A method, apparatus, non-transitory computer readable medium, and system for image generation include obtaining an input image including a source object and a target region. A target mask is computed based on the source object and the target region. The target mask has a shape of the source object and is located within the target region. An image generation model generates an output image based on the input image and the target mask, wherein the output image includes a synthetic variant of the source object in the target region.
Data privacy management techniques using probabilistic data structures are described. In one or more examples, a dataset record is received that includes an identity key, a respective attribute, and confidential information. A sketch is generated as a probabilistic data structure based on the identity key and the attribute. A mapping is formed of the confidential information to the sketch. The sketch is communicated to be stored in a database that supports a probabilistic result to a query operation.
A method, apparatus, non-transitory computer readable medium, and system for generating images using adaptive compression ratios include obtaining an input prompt, and generating a plurality of image tokens based on the input prompt. Each of the plurality of image tokens represents an image region. Embodiments then determine a dynamic selectivity value based on an image generation stage. Subsequently, embodiments perform an attention operation on a subset of the plurality of image tokens based on the dynamic selectivity value to obtain an attention output. Embodiments then generate, using an image generation model, a synthetic image based on the attention output.
Techniques for generating traversable three-dimensional scenes from text prompts are described and are implementable to create interactive virtual environments. In an example, a text-based query that specifies visual aspects of a desired three-dimensional scene is received. A spherical representation of the scene is generated by processing the query using one or more machine learning models. A traversable three-dimensional scene depicting the specified visual aspects is then constructed by processing the spherical representation using the one or more machine learning models. The traversable scene is output as part of a three-dimensional environment that allows navigation and viewing from multiple perspectives.
An analytics system jointly predicts values for multiple unobserved individual-level features using aggregate data for those features. Given a dataset, a transformation is applied to individual-level information for the dataset to generate transformed data in a higher dimensional space. Bag-wise mean embeddings are generated using the transformed data. The bag-wise mean embeddings and aggregate data for unobserved individual-level features for the dataset are used to train a model to jointly predict values for the unobserved individual-features for data instances. In particular, a given data instance can be transformed to a representation in a higher dimensional space. Given this representation, the trained model predicts values for the unobserved individual-level features for the data instance, and the data instance can be augmented with the predicted values.
G06N 20/10 - Apprentissage automatique utilisant des méthodes à noyaux, p. ex. séparateurs à vaste marge [SVM]
G06F 18/213 - Extraction de caractéristiques, p. ex. en transformant l'espace des caractéristiquesSynthétisationsMappages, p. ex. procédés de sous-espace
G06F 18/214 - Génération de motifs d'entraînementProcédés de Bootstrapping, p. ex. ”bagging” ou ”boosting”
G06Q 30/0242 - Détermination de l’efficacité des publicités
6.
DATA EXPLORATION USING NATURAL LANGUAGE WITH DATA SAMPLING
In various examples, an exploratory data analytics tool obtains a natural language query and generates a structured data query for execution on a sample of a dataset based on the natural language query. In an example, an intent is determined for the query and the intent is used, at least in part, to determine the most appropriate sample. In addition, the intent, in some examples, is used to generate recommended queries. A user interface of the exploratory data analytics tool, for example, can display the recommended queries and/or the results of the structured data query on the sample.
In implementations of systems for generating digital content, a computing device implements a generation system to receive a user input specifying a characteristic for digital content. The generation system generates input text based on the characteristic for processing by a first machine learning model. Output text generated by the first machine learning model based on processing the input text is received. The output text describes a digital content component. The generation system generates the digital content component by processing the output text using a second machine learning model. The generation system generates the digital content including the digital content component for display in a user interface based on the characteristic.
In implementations of techniques and systems for employing a training framework for diffusion models to track points in video generation, a processing device receives a training input of noisy video frames of a first digital video depicting a target object exhibiting a reference movement to train a machine-learning model. A denoiser of the machine-learning model is trained to remove noise from the noisy video frames of the first digital video by minimizing a diffusion loss that quantifies noise removal and data reconstruction. A refiner module of the machine-learning model is trained to refine latent features of the noisy video frames by minimizing a correspondence loss that quantifies a spatial correspondence among multiple points in the noisy video frames in relation to the reference movement. The trained machine-learning model is configured to generate a second digital video that depicts a particular object exhibiting a particular movement.
Video content creation is described. A video generation system employs a machine learning system to automate video generation, from textual input to final video output. The video generation system receives a textual description and optional parameters as user input and uses this input to generate a prompt for input to at least one machine learning model. The prompt causes the at least one machine learning model to output a summary understanding of the user-provided inputs along with a scene-by-scene script for a video. Based on the script, the video generation system automatically imports or generates visuals, synthesizes narration, and selects audio for each video scene. The video generation system is then configured to adjust individual scene elements for optimal cohesion and timing during video playback. In some implementations, the video generation system produces multiple video variations, enabling users to ideate by visualizing and comparing different options.
G11B 27/02 - Montage, p. ex. variation de l'ordre des signaux d'information enregistrés sur, ou reproduits à partir des supports d'enregistrement ou d'information
A method, apparatus, non-transitory computer readable medium, and system for data processing includes obtaining a data store and input text, where the data store includes data and the input text describes the data, generating a description of a structural element of the data, and generating attribution information for the input text based on the description of the structural element.
The present disclosure relates to systems, methods, and non-transitory computer-readable media that selects a set of vector paths in a vector graphic. Furthermore, the disclosed systems access a vector graphic that includes a set of shapes. Moreover, the disclosed systems generate a semantic mask of a semantic region in response to user input indicating a portion of the vector graphic. Further, the disclosed systems select a set of vector paths in the vector graphic that corresponds to a location of the semantic mask by using a polyline model. Additionally, the disclosed systems provide the selected set of vector paths as a selection of the semantic region.
Selective content recording is described. A web-based recording system leverages web application programming interfaces (APIs) to capture and synchronize multiple media streams simultaneously, including display content (e.g., application windows, browser tabs, and so forth) and user content (e.g., audio and video capturing a computing device user). The recording system operates within a web browser environment, eliminating the need for platform-specific installations or updates, and captures only portions of display content and portions of user content that are explicitly selected by a user. Selected portions of display media and selected portions of user media are rendered as separate elements on a single canvas, enabling real-time merging of different media streams via a web browser in a platform-agnostic manner.
G06F 3/04845 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] pour la commande de fonctions ou d’opérations spécifiques, p. ex. sélection ou transformation d’un objet, d’une image ou d’un élément de texte affiché, détermination d’une valeur de paramètre ou sélection d’une plage de valeurs pour la transformation d’images, p. ex. glissement, rotation, agrandissement ou changement de couleur
G06F 3/0482 - Interaction avec des listes d’éléments sélectionnables, p. ex. des menus
13.
HIGH DYNAMIC RANGE VISUALIZATIONS INDICATING RANGES, POINT CURVES, AND PREVIEWS
A high dynamic range editing system is configured to generate visualizations to aide digital image editing in both high dynamic ranges and standard dynamic ranges. In a first example, the visualization is generated as a histogram. In a second example, the visualization is generated to indicate high dynamic range capabilities. In a third example, the visualization is generated to indicate ranges of luminance values within a digital image. In a fourth example, the visualization is generated as a point curve that defines a mapping between detected luminance values from a digital image and output luminance values over both a standard dynamic range and a high dynamic range. In a fifth example, the visualization is generated as a preview to convert pixels from the digital image in a high dynamic range into a standard dynamic range.
An image processing system obtains an input image (e.g., a user provided image, etc.) and a mask indicating an edit region of the image. A user selects an image editing mode for an image generation network from a plurality of image editing modes. The image generation network generates an output image using the input image, the mask, and the image editing mode.
Three-dimensional object edit and visualization techniques and systems are described. In a first example, a content navigation control is implemented by a content editing system to aid navigation through a history of how a three-dimensional environment and a three-dimensional object included in the environment is created. In a second example, the content editing system is configured to streamline placement of a three-dimensional object within a three-dimensional environment. The content editing system, for instance, generates a manipulation visualization in support of corresponding editing operations to act as a guide, e.g., as an alignment guide or an option guide. In a third example, the content editing system implements a shadow control that is usable as part of an editing and as a visualization to control rendering of illumination within a three-dimensional environment.
G06T 19/20 - Édition d'images tridimensionnelles [3D], p. ex. modification de formes ou de couleurs, alignement d'objets ou positionnements de parties
G06F 3/04815 - Interaction s’effectuant dans un environnement basé sur des métaphores ou des objets avec un affichage tridimensionnel, p. ex. modification du point de vue de l’utilisateur par rapport à l’environnement ou l’objet
G06F 3/04845 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] pour la commande de fonctions ou d’opérations spécifiques, p. ex. sélection ou transformation d’un objet, d’une image ou d’un élément de texte affiché, détermination d’une valeur de paramètre ou sélection d’une plage de valeurs pour la transformation d’images, p. ex. glissement, rotation, agrandissement ou changement de couleur
G06F 3/04847 - Techniques d’interaction pour la commande des valeurs des paramètres, p. ex. interaction avec des règles ou des cadrans
G06T 19/00 - Transformation de modèles ou d'images tridimensionnels [3D] pour infographie
16.
GENERATING SUBJECT LINES FROM KEYWORDS UTILIZING A MACHINE-LEARNING MODEL
The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize machine learning to generate subject lines from subject line keywords. In one or more embodiments, the disclosed systems receive, from a client device, one or more subject line keywords. Additionally, the disclosed systems generate, utilizing a subject generation machine-learning model having learned parameters, a subject line by selecting one or more words for the subject line from a word distribution based on the one or more subject line keywords. The disclosed systems further provide, for display on the client device, the subject line.
Various disclosed embodiments are directed to deriving, via a language model, a summary of data by converting or encoding table data into one or more natural language sentences, which are then used as input to the language model for generating the summary. One or more embodiments are additionally or alternatively directed to deriving, via a language model, a response to a user question or command via a chat interface by providing the language model with the generated summary as input. In this way, for example, the language model can use the summary as a prompt or other target context for providing a response.
Digital video editing techniques are described that are based on a target digital image. In one or more implementations, inputs are received. The inputs include a target text prompt, a target digital image depicting a target object, and a source digital video having a plurality of frames depicting a source object. Regions-of-interest are identified in the plurality of frames of the source digital video, respectively, based on the target text prompt and the target digital image using a machine-learning model, e.g., a diffusion model. A plurality of frames of a target digital video are generated as having the target object using a generative machine-learning model. The generating is based on the regions-of-interest, the target digital image, the source digital video, and a source text prompt describing the source digital video.
The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate joint-based segmentation masks for digital objects portrayed in digital videos. In particular, in one or more embodiments, the disclosed systems utilize a video masking model having a pose tracking neural network and a segmentation neural network to generate the joint-based segmentation masks. To illustrate, in some embodiments, the disclosed systems utilize the pose tracking neural network to identify a set of joints of the digital object across the frames of the digital video. The disclosed systems further utilize the segmentation neural network to generate joint-based segmentation masks for the video frames that portray the object using the identified joints. In some cases, the segmentation neural network includes a multi-layer perceptron mixer layer for mixing visual features propagated via convolutional layers.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating segmentation masks for a digital visual media item. In particular, in one or more embodiments, the disclosed systems generate, utilizing a neural network encoder, high-level features of a digital visual media item. Further, the disclosed systems generate, utilizing the neural network encoder, low-level features of the digital visual media item. In some implementations, the disclosed systems generate, utilizing a neural network decoder, an initial segmentation mask of the digital visual media item from the low-level features. Moreover, the disclosed systems generate, utilizing the neural network decoder, a refined segmentation mask of the digital visual media item from the initial segmentation mask and the high-level features.
G06V 10/26 - Segmentation de formes dans le champ d’imageDécoupage ou fusion d’éléments d’image visant à établir la région de motif, p. ex. techniques de regroupementDétection d’occlusion
G06V 10/77 - Traitement des caractéristiques d’images ou de vidéos dans les espaces de caractéristiquesDispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant l’intégration et la réduction de données, p. ex. analyse en composantes principales [PCA] ou analyse en composantes indépendantes [ ICA] ou cartes auto-organisatrices [SOM]Séparation aveugle de source
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
G06V 20/70 - Étiquetage du contenu de scène, p. ex. en tirant des représentations syntaxiques ou sémantiques
Context-based prompt generation techniques for generative machine-learning models are described. In one or more examples, a user interface (UI) selection of a UI element of first digital content is received. A processing device captures contextual information associated with the UI selection. A machine-learning model generates a prompt based on the UI selection and the contextual information. Generative artificial intelligence (AI) generates second digital content based on the prompt. The generative AI is implemented using one or more machine-learning models. The processing device then presents the second digital content for display in a user interface.
G06F 16/38 - Recherche caractérisée par l’utilisation de métadonnées, p. ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement
G06F 16/958 - Organisation ou gestion de contenu de sites Web, p. ex. publication, conservation de pages ou liens automatiques
22.
GENERATING VIDEO FROM AN IMAGE BASED ON VARIABLE SPEED
In implementation of techniques for generating video from an image based on variable speed, a computing device implements a variable speed system to receive a static digital image displayed in a user interface, an indication of a movement direction, and an indication of a variable rate of speed. The variable speed system generates a digital video based on the static digital image, the digital video having pixels that move in the movement direction at a speed that varies based on the variable rate of speed based on pixels from the static digital image. The variable speed system then displays the digital video in the user interface.
A method, apparatus, non-transitory computer readable medium, and system for obtaining a first image depicting a first font in a first language. An image encoder model is configured to encode the first image to obtain a first image embedding representing the first font. The image encoder model computes a similarity score between the first font and a second font in a second language based on the first image embedding and subsequently selects the second font as a similar font to the first font in the second language based on the similarity score. Then, a document with the second font in the second language is generated based on the selection of the second font as the similar font to the first font
G06F 40/58 - Utilisation de traduction automatisée, p. ex. pour recherches multilingues, pour fournir aux dispositifs clients une traduction effectuée par le serveur ou pour la traduction en temps réel
G06F 40/109 - Maniement des polices de caractèresTypographie cinétique ou temporelle
G06V 20/62 - Texte, p. ex. plaques d’immatriculation, textes superposés ou légendes des images de télévision
24.
ALIGNING AND DISTRIBUTING GRAPHICAL OBJECTS ACROSS VECTOR SPLINES
The present disclosure relates to systems, non-transitory computer-readable media, and methods for aligning and distributing digital objects along vector splines within digital design document. For example, the disclosed systems generate an accumulated length repository comprising accumulated lengths of a plurality of curve segments along a vector spline. Based on a uniform distance for placing a plurality of design objects along the vector spline, the disclosed systems search the accumulated length repository to identify selected curve segments from the plurality of curve segments for placing the plurality of design objects and generate a plurality of placement locations along the selected curve segments based on the uniform distance. Accordingly, in some embodiments, the disclosed systems generate a modified digital design document by placing the plurality of design objects at the plurality of placement locations.
In various examples, a workflow assistant tool utilizes a machine learning model to automate the creation and modification of workflow activities for an application based in a natural language input. For example, the workflow assistant tool leverages natural language processing (NLP) and machine learning models to interpret user queries, generate discrete segments and conditions, identify relevant data schemas, and produce executable data objects in a domain-specific language. In another example, the workflow assistant tool includes a multistep Retrieval-Augmented Generation-based prompt engineering pipeline in addition to schema filtering, segment and condition generation, and validation and correction mechanisms to generate workflow activities based on natural language inputs from a user.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating, utilizing a diffusion model, digital images depicting portraits relit according to a new lighting scheme. In particular, in some embodiments, the disclosed systems generate, utilizing a diffusion model, a first noised image based on a first digital image comprising a portrait of a subject and based on an environment map defining a new lighting scheme for the subject. In addition, in some embodiments, the disclosed systems generate, utilizing the diffusion model, a second noised image based on the environment map and a text prompt comprising a description of the subject. Furthermore, in some embodiments, the disclosed systems generate, utilizing the diffusion model, a new digital image comprising a relit portrait of the subject by combining the first noised image and the second noised image.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating three-dimensional Gaussian reconstructions of a three-dimensional scene. In one or more embodiments, the disclosed systems determine an initial set of token sequences representing a set of digital images depicting a set of views of a three-dimensional scene according to corresponding camera pose parameters. The disclosed systems utilize a set of parallel state space blocks in a hybrid feed-forward neural network to generate a set of modified token sequences from the initial set of token sequences by mixing token information. The disclosed systems utilize a transformer block in the hybrid feed-forward neural network to generate a set of output token sequences from the set of modified token sequences. The disclosed systems generate a three-dimensional Gaussian reconstruction of the three-dimensional scene for synthesizing digital images depicting the three-dimensional scene with novel views from the set of output token sequences.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating a modified vector graphic for display by propagating a constraint entity. In one or more embodiments, the disclosed systems determine a constraint entity comprising a constraint type defining execution logic for the constraint entity and further comprising a set of constraint objects of the constraint type for a vector graphic. The disclosed systems detect a client device interaction modifying a constraint object within the set of constraint objects defined by the constraint entity. The disclosed systems generate a modified constraint entity in response to the interaction modifying the constraint object by updating the constraint entity according to the constraint type to reflect corresponding modifications to one or more related constraint objects within the set of constraint objects. The disclosed systems generate a modified vector graphic depicting the modified constraint entity for display on the client device.
Embodiments are disclosed for music generation. The method may include obtaining a music representation. A high-fidelity vocoder can then generate low-resolution audio data based on the music representation. A bandwidth extension module generates high-resolution monophonic audio data based on the low-resolution audio data and the music representation. A mono-to-stereo module generates high-resolution stereophonic audio data based on the high-resolution monophonic audio data.
G10H 1/02 - Moyens pour contrôler la fréquence des sons, p. ex. attaque ou affaiblissementMoyens pour produire des effets musicaux particuliers, p. ex. vibratos ou glissandos
30.
CONTENT OPTIMIZATION USING ARTIFICIAL INTELLIGENCE AGENTS
Techniques for optimizing digital content information are described. A conversion detection module identifies a set of conversion elements encoded into digital content information using a machine learning (ML) model. A content selection module selects a candidate conversion element from the set of conversion elements. A content block module identifies a candidate content block comprising the candidate conversion element and context information associated with the candidate conversion element. A prompt generation module generates a prompt for a generative artificial intelligence (GAI) agent, the prompt including the candidate content block and instructions to generate a content block variant comprising the candidate conversion element and a context information variant for the context information associated with the candidate conversion element. A content update module receives the content block variant from the GAI agent. The content update module presents the content block variant on a graphical user interface (GUI). Other embodiments are described and claimed.
This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that utilize a diffusion model to novel views of an entity depicted in a prompt image from a prompt view. For example, one or more implementations involve receiving a prompt image depicting a visual entity from a first viewpoint. Furthermore, one or more implementations involve generating, utilizing a diffusion model with an input camera condition and the prompt image, three-dimensional Gaussian point clouds representing the visual entity from a second viewpoint. Additionally, one or more implementations involve utilizing the 3D Gaussian point clouds to generate a new image depicting the visual entity from the second viewpoint.
H04N 13/279 - Générateurs de signaux d’images à partir de modèles 3D d’objets, p. ex. des signaux d’images stéréoscopiques générés par ordinateur les positions des points de vue virtuels étant choisies par les spectateurs ou déterminées par suivi
32.
DETECTING AND CREATING INTERTWINED GRAPHICS IN VECTOR-BASED DESIGNS
The present disclosure relates to systems, non-transitory computer-readable media, and methods for detecting and creating intertwine groups of vector objects in vector-based designs. In particular, the disclosed systems access a vector graphic file comprising a plurality of vector objects. Additionally, the disclosed systems determine, by at least one processor, that the plurality of vector objects comprises an intertwined group of vector objects. For example, the disclosed systems determine that the plurality of vector objects comprise one or more clipping groups. Moreover, the disclosed systems determine that the one or more clipping groups are spatially mutually exclusive or a non-clipping path object intersects with a union of clipping path boundaries of the one or more clipping groups.
G06T 11/20 - Traçage à partir d'éléments de base, p. ex. de lignes ou de cercles
G06F 3/04845 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] pour la commande de fonctions ou d’opérations spécifiques, p. ex. sélection ou transformation d’un objet, d’une image ou d’un élément de texte affiché, détermination d’une valeur de paramètre ou sélection d’une plage de valeurs pour la transformation d’images, p. ex. glissement, rotation, agrandissement ou changement de couleur
G06T 11/60 - Édition de figures et de texteCombinaison de figures ou de texte
33.
INTELLIGENT GENERATION OF ANALYTICS PRESENTATIONS BASED ON INSIGHTS EXTRACTED FROM ANALYTICS DATA AND NARRATIVE GROUPINGS
The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a digital presentation from a set of insights. Furthermore, the disclosed systems generate a set of insights from data extracted from an analytics application by using an intelligent captioning model. Moreover, the disclosed systems generate narrative grouping structures from the set of insights by grouping insights together based on similarity scores of the set of insights. Further, the disclosed systems generate a digital presentation outline according to the narrative grouping structures. From the digital presentation outline, the disclosed systems generate a digital presentation.
A method, apparatus, non-transitory computer readable medium, and system includes obtaining a digital image including a content area and a vignette border area including a first corner area at a first corner of the digital image and a second corner area at a second corner of the digital image, generating a preliminary border mask indicating a location of the vignette border area, where the preliminary border mask includes the first corner area and the second corner area, modifying the preliminary border mask by mirroring the first corner area, comparing the mirrored first corner area to the second corner area, and updating the preliminary border mask based on the comparison to obtain a modified border mask, and generating a generated image based on the digital image and the modified border mask, where the generated image includes the content area and a generated area corresponding to the vignette border area.
The present disclosure relates to systems, methods, and non-transitory computer-readable media that detects shadows, removes shadows, and synthesizes shadows in a joint-framework. In particular, the disclosed systems access an object mask of an object and a digital image depicting the object and a shadow of the object. Furthermore, the disclosed systems perform object-centered shadow detection and removal to generate a modified digital image without the shadow by utilizing a shadow analyzer model. Moreover, the disclosed systems receive a user interaction to manipulate an object and generate a modified shadow utilizing a shadow synthesis model where the shadow synthesis model is conditioned on a shadow mask generated by the shadow analyzer model.
Implementations of systems and methods for determining viewpoints suitable for performing one or more digital operations on a three-dimensional object are disclosed. Accordingly, a set of candidate viewpoints is established. The subset of candidate viewpoints provides views of an outer surface of a three-dimensional object and those views provide overlapping surface data. A subset of activated viewpoints is determined from the set of candidate viewpoints, the subset of activated viewpoints providing less of the overlapping surface data. The subset of activated viewpoints is used to perform one or more digital operation on the three-dimensional object.
H04N 13/279 - Générateurs de signaux d’images à partir de modèles 3D d’objets, p. ex. des signaux d’images stéréoscopiques générés par ordinateur les positions des points de vue virtuels étant choisies par les spectateurs ou déterminées par suivi
In implementation of techniques for removing image overlays, a computing device implements a reflection removal system to receive an input RAW digital image, the input RAW digital image including both a base image and an overlay image. Using a machine learning model, the reflection removal system segments the base image from the overlay image. The reflection removal system generates an output RAW digital image that includes the base image and displays the output RAW digital image in a user interface.
In implementation of techniques for progressively generating fine polygon meshes, a computing device implements a mesh progression system to receive a coarse polygon mesh. The mesh progression system generates a fine polygon mesh that has a higher level of resolution than the coarse polygon mesh by decoding the coarse polygon mesh using a machine learning model. The mesh progression system then receives additional data describing a residual feature of a polygon mesh. Based on the additional data, the mesh progression system generates an adjusted fine polygon mesh that has a higher level of resolution than the fine polygon mesh.
The present disclosure relates to systems, methods, and non-transitory computer-readable media that recolors a digital design according to colors of a digital image and further generates an enhanced recolored digital design. In particular, in some embodiments, the disclosed systems identify a digital image for recoloring a digital design and recolors the digital design utilizing a color affine transformation algorithm to generate a recolored digital design. Further, in some embodiments, the disclosed systems generate the enhanced recolored digital design by transforming one or more colors of the recolored digital design to be within a range of the colors of the digital image utilizing a convex hull projection method. Moreover, in some embodiments, the disclosed systems further enhance the recolored digital design utilizing a contrast enhancement algorithm to modify luminescence values.
Database query translation and schema synthesis techniques are described. These techniques support training data generation usable to train a machine-learning model to translate a natural language query into a database query. A database system is configurable to address a variety of evolution types to a database schema in support of machine-learning model training through use of a training data generation module. The training data generation module is configurable to generate database query variations that address different types of database schema evolutions. An evaluation module is also configurable as part of the database system to evaluate operability of a trained machine-learning model to perform query translation using an evaluation module.
A method, apparatus, non-transitory computer readable medium, and system for improving text legibility in generated images include processing an input prompt that indicates a visual text. An image generation model performs a first cross-attention operation based on the input prompt and a second cross-attention operation based on the visual text. The image generation model then generates a synthetic image depicting the visual text by combining results from both cross-attention operations.
A method, apparatus, non-transitory computer readable medium, and system for reducing hallucinations in visual captions includes obtaining an image and an input caption for the image. An image perception system then decomposes the input caption into a plurality of partial captions, where each partial caption can be independently verified to detect hallucinations. Each of the plurality of partial captions includes a portion of the input caption. The system then generates an output caption for the image based on the plurality of partial captions, where portions identified as hallucinations are excluded. The output caption excludes the portion of the input caption corresponding to a partial caption of the plurality of partial captions.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for dynamically generating and providing customized color palettes based on a light source color. In particular, in one or more embodiments, the disclosed systems provide, via a graphical user interface, a first color palette comprising a first set of colors corresponding to a first light source color. The disclosed systems receive, via the graphical user interface, user input indicating a user selection of a second light source color. The disclosed systems generate, based on the user input and the first set of colors, a second color palette comprising a second set of colors corresponding to the second light source color. The disclosed systems provide, via the graphical user interface and in response to the user input, the second color palette comprising the second set of colors corresponding to the second light source color.
A method, apparatus, non-transitory computer readable medium, and system for image processing include obtaining a subject image and a pose image, where the subject image depicts an object and the pose image depicts a target pose, obtaining keypoint information that associates a part of the subject image and a corresponding part of the pose image, generating a flow map indicating a transformation of the part of the subject image by generating a plurality of flow map features at a plurality of different resolutions at different layers of the warping model, respectively, and generating a warped image based on the flow map and the subject image, where the warped image depicts the object with the target pose.
The present disclosure is directed toward systems, methods, and non-transitory computer readable media that finetune large language models for code generation based on code execution results using preference-guided learning. For example, the disclosed systems utilize a large language model to generate a set of code responses from a natural language query, wherein the set of code responses correspond to code. Furthermore, the disclosed systems compare the set of code responses to a ground truth code response to generate a set of correct code responses and a set of incorrect code responses. The disclosed systems generate a preference dataset from preference pairs selected from the set of correct code responses and the set of incorrect code responses. In addition, the disclosed systems finetune the large language model by modifying parameters of the large language model to reduce incorrect code responses according to a loss function based on the preference dataset.
A large language model (LLM)-based scene generator receives a natural language prompt including instructions to generate a three-dimensional scene. The LLM-based scene generator generates, using a first machine-learning model, a scene graph based on the natural language prompt. The first machine-learning model generates the scene graph by generating a representation of one or more objects oriented within a two-dimensional environment of the scene graph and subdividing the two-dimensional environment into one or more subparts. The one or subparts represent contextually distinct portions of the two-dimensional environment. The LLM-based scene generator modifies a representation of a subpart of the one or more subparts by adding additional objects within the subpart. The additional objects are contextually related to the subpart. The LLM-based scene generator renders the scene graph into the three-dimensional scene using a second machine-learning model. The LLM-based scene generator generates the three-dimensional scene.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for managing and reusing chunk caches in processing a user query via a large language model. For example, the disclosed systems extract a first plurality of text chunks relevant to an input query, where the first plurality is arranged in a first sequence. In some embodiments, the disclosed systems determine, according to a second plurality of text chunks, a precomputed key-value cache for a text chunk of the first plurality of text chunks. The disclosed systems determine a cache reusability score for the text chunk according to dependency metrics of tokens within the text chunk and tokens within a second plurality of text chunks. In various embodiments, the disclosed systems reuse, within the large language model generating a response to the input query, the precomputed key-value cache associated with the text chunk based on the cache reusability score.
Three-dimensional object edit and visualization techniques and systems are described. In a first example, a content navigation control is implemented by a content editing system to aid navigation through a history of how a three-dimensional environment and a three-dimensional object included in the environment is created. In a second example, the content editing system is configured to streamline placement of a three-dimensional object within a three-dimensional environment. The content editing system, for instance, generates a manipulation visualization in support of corresponding editing operations to act as a guide, e.g., as an alignment guide or an option guide. In a third example, the content editing system implements a shadow control that is usable as part of an editing and as a visualization to control rendering of illumination within a three-dimensional environment.
Methods and systems are provided for using comparative statistical tests to rank content attribute values for a target audience. In embodiments described herein, historical content and corresponding historical performance metrics are accessed. Attribute values of content attributes are determined from the historical content. A ranked set of content attributes is determined based on a computed impact of the attribute values of a particular content attribute on the corresponding historical performance metric. A ranked set of attribute values is determined by scoring each attribute value using a comparative statistical test to compare the historical performance metric of each content asset with the attribute value to the historical performance metric of each remaining content asset without the attribute value. The ranked set of content attributes and the ranked set of attribute values are displayed or utilized by a generative artificial intelligence model to generate content.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating machine-learning based action recommendations for display on a client device. In particular, the disclosed systems generate, utilizing a context aware neural network, a first set of action recommendations for editing a digital document based on contextual data from content of the digital document. Additionally, the disclosed systems generate, utilizing a user persona model, a second set of action recommendations for editing the digital document based on user specific data of a user account editing the digital document. Further, the disclosed systems determine, utilizing an ensemble model, one or more selected action recommendations from the first set of action recommendations or the second set of action recommendations. Moreover, the disclosed systems provide, for display on a client device, the one or more selected action recommendations within a graphical user interface including the digital document.
A method, apparatus, non-transitory computer readable medium, and system for answering queries about an image include obtaining an image and a query about the image. An image perception system then generates an action based on the image and the query using an orchestrator vision-language model. The image perception system then generates vision analysis result based the image and the action using a vision expert model. The image perception system then generates an answer to the query based on the vision analysis result.
G06V 10/70 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique
G06F 16/3329 - Formulation de requêtes en langage naturel
G06V 10/80 - Fusion, c.-à-d. combinaison des données de diverses sources au niveau du capteur, du prétraitement, de l’extraction des caractéristiques ou de la classification
52.
WIRELESSLY CONTROLLING SERVER-HOSTED APPLICATIONS WITH MOBILE DEVICES
The present disclosure relates to systems, non-transitory computer readable media, and methods for providing a virtual controller for interacting with a server-hosted digital media application. In one or more embodiments, the disclosed systems determine, by a secondary client device via a local network, connection information for an open connection channel established with an application server hosting a digital media editing application via a primary client device running an active session of the digital media editing application. In some embodiments, the disclosed systems provide a control user interface on the secondary client device for interacting with the active session running on the primary client device. In some embodiments, in response to receiving a user interaction via the control user interface, the disclosed systems send an instruction from the secondary client device to the application server to control the active session of the digital media editing application via the open connection channel.
09 - Appareils et instruments scientifiques et électriques
42 - Services scientifiques, technologiques et industriels, recherche et conception
Produits et services
Electronic apparatus and instruments and parts therefor; typeface fonts recorded on magnetic recording media; downloadable fonts provided by electronic transmission means; downloadable computer software for creating fonts; downloadable typeface computer software; type designs recorded as latent images in machine-readable data storage media; data carriers containing stored typographic typefaces; software for generating, displaying, and printing fonts and font combinations; computer software for creating typefaces; computer software for generation of typefaces and font. Providing temporary use of non-downloadable font, typeface computer software for use online and on web sites; computer and computer software consulting services; technical support services; providing on-line support services for computer program users, all of the foregoing in relation to font and typeface software; creating an online community for registered users to generate, display, and print fonts and font combinations and view information related to fonts, participate in font collaboration, create, share, store and download fonts and font combinations, showcase fonts and font combinations, get feedback from their peers, form virtual communities, engage in social networking, and improve their skills; providing temporary use of online non-downloadable software; providing temporary use of non-downloadable software for generating, displaying, and printing fonts and font combinations; providing technical information in the fields of fonts, font software and typography via the internet; design of typeface.
In implementations of techniques and systems for volumetric sculpting using dual contouring, a processing device determines and stores signed distance values of vertices in a voxel grid with multiple grid cells to represent a 3D object. The processing device also determines and stores the position and state of feature points within grid cells. The feature points indicate a geometric feature of the 3D object within a corresponding grid cell. The processing device then uses dual contouring on the signed distance values and feature points to render a mesh of the 3D object.
A method, apparatus, non-transitory computer readable medium, and system for data processing includes obtaining a query relating to a set of documents, generating a plurality of first interpretations of the query, retrieving a plurality of text passages from the set of documents based on the plurality of first interpretations, and generating a response to the query based on the plurality of text passages.
A method, apparatus, non-transitory computer readable medium, and system for generating a synthetic image includes obtaining a first prompt indicating a foreground object and a second prompt indicating a background scene. A first image generation model is configured to generate a foreground attention output based on the first prompt, wherein the foreground attention output represents the foreground object. In some cases, a second image generation model is configured to generate a blended attention output based on the first prompt and the second prompt, wherein the blended attention output represents the foreground object with the background scene. The foreground attention output and the blended attention output are combined to obtain a combined blended attention output. Subsequently, the second image generation model generates a synthetic blended image depicting the foreground object in the background scene based on the combined blended attention output.
In implementation of techniques for generating a latent space for a three-dimensional scene, a computing device implements a latent space system to receive a three-dimensional representation of a scene. Using a machine learning model, the latent space system encodes a tokenized three-dimensional representation based on the three-dimensional representation of the scene into a latent space. The latent space system then decodes three-dimensional information related to the scene from the latent space using the machine learning model.
Techniques for shape aware descriptive movement synthesis are described. In an example, a processing device is operable to receive a description of a body motion and a body, used as input to a trained machine learning system that generates motion data from the description. A shape parameter and a plurality of motion tokens are jointly predicted by the machine learning system based on the description. A plurality of discrete motion features is obtained from applying a finite scalar de-quantization to the motion tokens. Using the machine learning system, the processing device generates a plurality of shape conditioned motion features by integrating a shape feature projected from the shape parameter with the discrete motion features. The shape conditioned motion features are decoded by the machine learning system into the motion data, which models the motion with specific variations caused by the shape.
The present disclosure relates to systems, methods, and non-transitory computer-readable media that vectorize raster images while translating transmissive properties portrayed therein. For instance, one or more embodiments involve receiving a raster image that includes a set of pixels having a transmissive property and extracting a plurality of segments from the raster image using a segmentation model. Some embodiments further involve generating, from the raster image, a segment-to-pixel mapping that maps a segment from the plurality of segments to the set of pixels having the transmissive property. Using the segment-to-pixel mapping, some embodiments vectorize the raster image by generating a vector graphic having a vector path that corresponds to the segment and includes the transmissive property. Some implementations further provide the vector graphic for display.
An application blueprint analysis system is described. In one or more examples, a communicative connection is established with a monitoring module configured to monitor user interaction with an application at a monitored computing device. The blueprint analysis system receives interaction data describing the monitored user interaction as a plurality of events. The events include captures of respective user interfaces involved in the monitored user interaction and navigational relationships of the user interfaces to each other. The blueprint analysis system forms an element visualization having an element hierarchy based on the navigational relationships and including the captures of the respective user interfaces. The blueprint analysis system then presents the element visualization for display in an analysis user interface.
The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a vector graphic image from a modified diffusion curve. Furthermore, the disclosed systems generate Monte Carlo rendering color estimates for corresponding subpoints of an image of a three-dimensional digital scene. Moreover, the disclosed systems generate Monte Carlo PDE color estimates for corresponding subpositions within a target image of the three-dimensional digital scene by using Monte Carlo PDE model parameterized by a diffusion curve. Further, the disclosed systems generate a modified diffusion curve from the diffusion curve by comparing the Monte Carlo rendering color estimates with the Monte Carlo PDE color estimates. From the modified diffusion curve, the disclosed systems generate the vector graphic image of the three-dimensional digital scene.
A journey map system is configured to employ a machine-learning model to assign category tags to historical journey maps. The journey map system then generates clusters based on similarities between these journey maps. Effectiveness of these clusters in performing an operation is determined by the journey map system using performance indicator data. The journey map system identifies representative journey maps based on the performance indicator data, the clusters, and the category tags. Finally, the journey map system generates insights using a language model implemented with machine learning.
In accordance with the described techniques for attribution in contextual question answering using large-language-model hidden states, a processing device receives a document and an answer formulated by a first machine-learning model from the content of the document. A second machine-learning model decomposes the answer into one or more answer tokens and attributes each answer token to one or more document tokens of the document. The processing device then generates an annotated document that includes at least one visual indication associating one or more answer tokens with one or more document tokens.
The present disclosure is directed toward systems, methods, and non-transitory computer readable media that generate, for display via a graphical user interface, a digital image portraying a variety of materials, wherein one of the materials includes a first sub-material and a second sub-material which are visually distinct. The disclosed systems receive, via an interaction with the graphical user interface, a selection of a location on the digital image corresponding to the first sub-material. Furthermore, the disclosed systems generate, based on the selection and utilizing a material detection neural network, a first material selection that includes an indication of pixels of the digital image displaying the material and a second material selection that includes an indication of pixels of the digital image displaying the first sub-material. In addition, the disclosed systems provide, via the graphical user interface, the first material selection and the second material selection.
G06V 10/94 - Architectures logicielles ou matérielles spécialement adaptées à la compréhension d’images ou de vidéos
G06V 10/26 - Segmentation de formes dans le champ d’imageDécoupage ou fusion d’éléments d’image visant à établir la région de motif, p. ex. techniques de regroupementDétection d’occlusion
G06V 10/52 - Analyse spatiale multi-échelle, p. ex. analyse par ondelettes
G06V 10/75 - Organisation de procédés de l’appariement, p. ex. comparaisons simultanées ou séquentielles des caractéristiques d’images ou de vidéosApproches-approximative-fine, p. ex. approches multi-échellesAppariement de motifs d’image ou de vidéoMesures de proximité dans les espaces de caractéristiques utilisant l’analyse de contexteSélection des dictionnaires
G06V 10/77 - Traitement des caractéristiques d’images ou de vidéos dans les espaces de caractéristiquesDispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant l’intégration et la réduction de données, p. ex. analyse en composantes principales [PCA] ou analyse en composantes indépendantes [ ICA] ou cartes auto-organisatrices [SOM]Séparation aveugle de source
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
G06V 20/70 - Étiquetage du contenu de scène, p. ex. en tirant des représentations syntaxiques ou sémantiques
65.
LEARNING BASED ASSESSMENT OF MULTI-SHOT VIDEO CLIP ASSEMBLIES
Techniques for learning based assessment of clip assemblies for multi-shot videos are described. In an example, a processing device is operable to receive a plurality of single-shot video clips and generate embeddings of each of the single-shot video clips using a machine learning model. The processing device is further operable to transform the embeddings into a video representation using the machine learning model and determine a learned quality score of a multi-shot video sequence assembled from the single-shot video clips by processing the video representation through a regression layer of the machine learning model. The processing device is configurable to output the learned quality score as a measure of assembly quality for the multi-shot video sequence.
G06V 10/74 - Appariement de motifs d’image ou de vidéoMesures de proximité dans les espaces de caractéristiques
G06V 10/774 - Génération d'ensembles de motifs de formationTraitement des caractéristiques d’images ou de vidéos dans les espaces de caractéristiquesDispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant l’intégration et la réduction de données, p. ex. analyse en composantes principales [PCA] ou analyse en composantes indépendantes [ ICA] ou cartes auto-organisatrices [SOM]Séparation aveugle de source méthodes de Bootstrap, p. ex. "bagging” ou “boosting”
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
G06V 20/40 - ScènesÉléments spécifiques à la scène dans le contenu vidéo
G11B 27/031 - Montage électronique de signaux d'information analogiques numérisés, p. ex. de signaux audio, vidéo
66.
DISENTANGLING DESIGN ELEMENTS FOR CODE COMPONENT GENERATION
code components by disentangling content, structure, and style. In accordance with some aspects, content is extracted from a UI design file for a UI design generated using an interface design application. Structure data is inferred from a screenshot of the UI design. Additionally, style data is extracted from the UI design file. Structure code is generated using the structure data, styling code is generated using the style data, and the structure code and the styling code are stored in a code repository as code components for the UI design.
Relationship classifier and query scope control techniques are described as implemented by a question answering system. By employing a classifier machine-learning model trained on both user-generated and machine-generated queries, the question answering system is configured to accurately determine whether a product query is within the scope of processing capabilities of corresponding product machine-learning models. The question answering system also supports an ability to generate machine-generated queries with increasing levels of abstraction that further supports comprehensive training data. Additionally, a sampling technique may be used by the question answering system as part of training data generation in order to promote a balanced training dataset.
Some aspects relate to technologies for enhanced data sampling for expert tasks during model adaptation and/or evaluation. In accordance with some aspects, a first subset of datapoints is sampled from a dataset and provided to an expert for an expert task for adapting or evaluating a target model. Task difficulty scores are obtained for the first subset of datapoints based on a difficulty in performing the expert task for each datapoint. A difficulty prediction model is trained using the first subset of datapoints and their corresponding task difficulty scores. Using the difficulty prediction model, task difficulty scores are generated for other datapoints from the dataset not in the first subset of datapoints. A second subset of datapoints is sampled from the other datapoints based on the task difficulty scores for the other datapoints. The second subset of datapoints are provided to the expert for performance of the expert task.
Techniques for multiview inpainting of three-dimensional (3D) objects are described. In one or more examples, a processing device receives a first three-dimensional (3D) object, a mask indicating a region of the first 3D object in which to inpaint a second 3D object, and a text description of the second 3D object. A first machine-learning model generates multiple two-dimensional (2D) views of the first 3D object and the mask. For each 2D view, the first machine-learning model generates a third 3D object that includes the second 3D object inpainted on the first 3D object. A second machine-learning model reconstructs a 3D representation of the third 3D object from the multiple 2D views, which is presented for display in a user interface.
Techniques related to material glint generation for digital content are described. In an example, a processing device is operable to obtain a base model representing a material surface of a digital object, receive one or more glint parameters indicating glint effects applied to the material surface, and generate a glint model of the glint effects. The processing device is operable to generate the glint model by integrating a plurality of glint particles within the material surface based on the glint parameters. Using the glint model, the processing device is operable to render an image of the digital object depicting reflections from visible glint particles integrated within the material surface.
Some aspects relate to technologies providing a framework for training a brand-aligned image generation model to generate brand-aligned images. In accordance with some aspects, the brand-aligned image generation model is trained by first receiving a brand-aligned image and generating a caption describing the brand-aligned image. A non-brand-aligned image is generated from the caption using a generic image generation model. The brand-aligned image and the non-brand-aligned image form an image pair that is used to train the brand-aligned image generation model.
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
G06V 20/70 - Étiquetage du contenu de scène, p. ex. en tirant des représentations syntaxiques ou sémantiques
Techniques for sequential image generation and editing are described. In an example, a query that specifies visual aspects to be included in a generated image is received for processing by a machine learning model. The machine learning model is configured to sequentially generate various image components that represent the visual aspects. Each image component, e.g., a layout representation, a background representation, and/or one or more object representations, is conditioned on previously generated image components. A digital image that includes the visual aspects is generated by integrating the various image components using the machine learning model.
Techniques related to multimodal large language model 3D generation are described. In an example, a processing device is operable to input an object description into a large language model that creates an initial compact graph representing an initial hierarchy of initial object attributes based on the object description. The processing device generates an initial object model based on the initial compact graph. The processing device inputs an object edit into the large language model that creates an updated compact graph representing an updated hierarchy of updated object attributes and replaces the initial object model with an updated object model generated based on the updated compact graph.
The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a refined digital image that corrects inpainting artifacts in a modified digital image with inpainted pixels. Furthermore, the disclosed systems receive an inpainting request to inpaint a region in a digital image (e.g., a region indicated by a mask). Moreover, the disclosed systems generate a modified digital image from the inpainting request and the digital image, where the modified digital image includes one or more inpainted portions in place of the region. Further, the disclosed systems use a neural network-based refiner model to generate a refined digital image from the modified digital image that corrects artifacts around borders of the one or more inpainted portions in the modified digital image.
Techniques and systems for explanations of database query results by a virtual assistant are described. In an example, a processing device is operable to receive an input that includes a request in a natural language format related to a database. For example, the request is an instruction to create, alter, retrieve, delete, manage, or manipulate the database or data in the database. A first machine-learning model (e.g., a large language model (LLM)) generates a database query based on the request. The processing device queries the database using the database query to obtain a query result. A second machine-learning model generates a query explanation of the database query in the natural language format. The processing device then presents the query result and query explanation in a user interface.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating a synthesized digital image based on reference digital images and a case prompt. In one or more embodiments, the disclosed systems determine one or more reference digital images and a case prompt including a natural language description of a target digital image in response to a request. The disclosed systems utilize an encoder neural network to generate image patch embeddings from the one or more reference digital images with one or more role indicators for the one or more reference digital images and noise patch embeddings from latent noise. The disclosed systems combine the image patch embeddings, the noise patch embeddings, and a case prompt encoding to form a composite embedding. The disclosed systems utilize a diffusion neural network to generate a synthesized digital image based on the composite embeddings and the one or more role indicators.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing token tree-based restricted decoding in large language models to generate code for narrow AI domains. In particular, the disclosed systems determine a database schema of a database in response to a natural language prompt for a large language model to generate code for performing an operation on the database. Additionally, the disclosed systems restrict a decoding space of the large language model to tokens of a token tree representing elements of the database schema according to a tokenizer of the large language model. Further, the disclosed systems generate, utilizing the large language model, one or more portions of the code by traversing the tokens of the token tree according to token edges of the token tree and a decoded token sequence.
Techniques related to material glint generation for digital content are described. In an example, a processing device is operable to output a user interface that previews an object model and receive a material selection that designates a material part of the object model. The processing device is further operable to obtain a plurality of sample images showing different views of the object model and the material part designated by the material selection, input the sample images and the material selection into a material selector model that creates a similarity point cloud enabling material similarity querying across multiple material parts of the object model, and presents, via the user interface, an indication of different material parts of the object model that have a similar material as the material part designated by the material selection.
G06T 19/20 - Édition d'images tridimensionnelles [3D], p. ex. modification de formes ou de couleurs, alignement d'objets ou positionnements de parties
G06F 30/12 - CAO géométrique caractérisée par des moyens d’entrée spécialement adaptés à la CAO, p. ex. interfaces utilisateur graphiques [UIG] spécialement adaptées à la CAO
G06F 30/27 - Optimisation, vérification ou simulation de l’objet conçu utilisant l’apprentissage automatique, p. ex. l’intelligence artificielle, les réseaux neuronaux, les machines à support de vecteur [MSV] ou l’apprentissage d’un modèle
G06F 119/18 - Analyse de fabricabilité ou optimisation de fabricabilité
79.
GENERATING IN-APP STARTER ELEMENTS FOR THEME-BASED DIGITAL IMAGE EDITING UTILIZING GENERATIVE NEURAL NETWORKS
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating one or more interactive object elements consistent with a determined theme using a large language model in combination with an image generation neural network. For example, the disclosed systems determine, from a text input via a graphical user interface, a theme for inserting image content into a digital image within the graphical user interface. The disclosed systems generate, in response to the text input, a prompt indicating one or more objects related to the theme. The disclosed systems generate, by utilizing an image generation neural network, one or more object elements corresponding to the one or more objects related to the theme for display within the graphical user interface. In various embodiments, the disclosed systems provide the one or more object elements as one or more interactive object elements for inserting into the digital image.
G06T 11/60 - Édition de figures et de texteCombinaison de figures ou de texte
G06F 3/0482 - Interaction avec des listes d’éléments sélectionnables, p. ex. des menus
G06F 3/04845 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] pour la commande de fonctions ou d’opérations spécifiques, p. ex. sélection ou transformation d’un objet, d’une image ou d’un élément de texte affiché, détermination d’une valeur de paramètre ou sélection d’une plage de valeurs pour la transformation d’images, p. ex. glissement, rotation, agrandissement ou changement de couleur
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
80.
DETECTING AND REMOVING WIDOWS AND ORPHANS IN HIERARCHICAL TEXT
The present disclosure is directed toward systems, methods, and non-transitory computer readable media that adjust the display of hierarchical content to reduce disruption to text flow within a digital document. For example, the disclosed systems detect a hierarchical segment within a digital document that includes a hierarchical organization of elements in response to a selection of a document layout analysis tool via a graphical user interface. Furthermore, the disclosed systems detect an isolated element of the hierarchical segment positioned on a separate page or a separate column from other elements of the hierarchical segment. The disclosed systems determine a document layout penalty for the digital document based on a disruption to text flow within the digital document associated with the isolated element. In addition, the disclosed systems adjust display of the hierarchical segment by modifying attributes of the digital document to reduce the determined document layout penalty.
The present disclosure relates to systems, non-transitory computer-readable media, and methods that utilize a dynamic user interface and machine learning tools to generate data-driven digital content and multivariate testing recommendations for distributing digital content across computer networks. In particular, in one or more embodiments, the disclosed systems utilize machine learning models to generate digital recommendations at multiple development stages of digital communications that are targeted on particular performance metrics. For example, the disclosed systems utilize historical information and recipient profile data to generate recommendations for digital communication templates, fragment variants of content fragments, and content variants of digital content items. Ultimately, the disclosed systems generate multivariate testing recommendations incorporating selected fragment variants to intelligently narrow multivariate testing candidates and generate more meaningful and statistically significant multivariate testing results.
09 - Appareils et instruments scientifiques et électriques
Produits et services
(Based on 44(d) Priority Application)(Based on Intent to Use) Electronic application machinery and equipment and their components; typeface fonts recorded on magnetic recording media; downloadable fonts provided by electronic transmission means (Based on Intent to Use) downloadable computer software for creating fonts; downloadable typeface computer software
A method, apparatus, non-transitory computer readable medium, and system for video generation includes obtaining an input prompt describing a scene. A video generation model generates a first frame chunk and a second frame chunk based on the input prompt, wherein the first frame chunk includes a first token corresponding to a video frame and the second frame chunk includes a second token corresponding to the same video frame as the first token. Subsequently, the video generation model generates a synthetic video based on the set of frame tokens including the first frame chunk and the second frame chunk, wherein the synthetic video depicts the scene and includes the video frame.
In various examples, a multimodal question answering tool generates multimodal answers to queries. For example, a machine learning model generates a text answer to a query, the text answer snippets are compared to text snippets from a source document to determine attribution. Based on the attribution, multimodal data is obtained from the document and used to generate a prompt that, as a result of being provided to the machine learning model, causes the machine learning model to generate a multimodal answer.
Methods and systems are provided for detecting design commands from speech using natural language processing to generate design variations. In embodiments described herein, a user inputs speech indicating a desired design. Parameters of detected design commands mapped to particular design tools of a design application are detected from input speech. Design variations are generated based on the detected parameters of the detected design commands by applying the corresponding design tools. The user inputs subsequent speech indicating desired revisions to the design variations. Different parameters of detected design commands mapped to particular design tools of the design application are detected from the subsequent speech. New design variations are generated based on the detected different parameters by applying the corresponding design tools to the design variations. After the user reviews the new design variations, the design process iteratively continues until the user selects a final design.
The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate a hierarchy of masks for a selected object within a digital image. For example, in some embodiments, the disclosed systems receive a digital image and user input selecting one or more pixels within an object portrayed therein. Using a segmentation neural network, the disclosed systems determine a parent token corresponding to a first semantic level for the object and a child token corresponding to a second semantic level for the object that is hierarchically lower than the first semantic level. The disclosed systems further generate, using the segmentation neural network and from the tokens, a first mask that corresponds to the first semantic level and a second mask that corresponds to the second semantic level. The disclosed systems provide, for display, at least one of the first mask or the second mask.
G06V 20/40 - ScènesÉléments spécifiques à la scène dans le contenu vidéo
G06V 10/778 - Apprentissage de profils actif, p. ex. apprentissage en ligne des caractéristiques d’images ou de vidéos
G06V 10/82 - Dispositions pour la reconnaissance ou la compréhension d’images ou de vidéos utilisant la reconnaissance de formes ou l’apprentissage automatique utilisant les réseaux neuronaux
G06V 20/70 - Étiquetage du contenu de scène, p. ex. en tirant des représentations syntaxiques ou sémantiques
87.
RETRIEVER MACHINE-LEARNING MODEL TRAINING DATA GENERATION AND IMPLEMENTATION
A query system is described that supports retriever machine-learning model training data generation and implementation. The retriever machine-learning model is configured to retrieve examples for inclusion in a prompt formed from an input query that provide context for the query in performance of a corresponding task. The query system, in one or more examples, implements an alternating minimization technique for example selection that enhances in-context learning (ICL) performance for resources having few initial examples, e.g., for an initial resource. The query system is also configurable to incorporate example diversity that improves generalization and reduces bias in the retriever machine-learning model used to select the examples.
The present disclosure relates to systems, methods, and non-transitory computer-readable media that modifies parameters of a generative model based on enhancing pixels of images. Furthermore, the disclosed systems generate a modified digital image from a digital image by inpainting a region of the digital image. Moreover, the disclosed systems generate a first measure of loss based on comparing the modified digital image with a ground truth version of the digital image. Further, the disclosed systems generate a transformed modified digital image and a transformed ground truth image of the digital image by performing a color space transformation and further generates a second measure of loss. From the first measure of loss and the second measure of loss, the disclosed systems modify parameters of a generative model.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for discovering and mitigating robustness gaps in semantic parsing models utilizing deep learning. For example, in one or more embodiments, the disclosed systems extract, utilizing a natural language processing model, predicates from a set of semantic parsing examples comprising natural language queries and corresponding structural representations. Further, the disclosed systems determine clusters of semantic parsing examples according to similarities between respective predicates from the semantic parsing examples. Moreover, the disclosed systems generate, utilizing a target semantic parsing model, predicted structural representations of the natural language queries and determine respective correctness values for the clusters based on comparing the predicted structural representations and the corresponding structural representations. In some embodiments, the disclosed systems identify robustness gaps in the target semantic parsing model based on the respective correctness values and implement mitigating actions to address the identified gaps.
This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that utilize a large language model as a base model to generate and utilize digital page navigation predictions with a variety of downstream user activity prediction tasks. Indeed, in one or more instances, the disclosed systems utilize the digital page navigation predictions from the large language model to derive multiple downstream predictive user activity tasks. In particular, in one or more implementations, the disclosed systems utilize the digital page navigation predictions with a variety of downstream user activity prediction models to generate user activity predictions for a user associated with the digital page navigation predictions. Moreover, in one or more implementations, the disclosed systems train a large language model to predict page sequences using a page order agnostic and contrastive measure of loss from training input-output page sequence pairs.
The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating layered digital design documents from sketches utilizing deep learning. In particular, the disclosed systems determine at least one of a canvas size or an aspect ratio of a sketch image. Additionally, the disclosed systems generate, based on the at least one of the canvas size or the aspect ratio, a compositional reference of the sketch image utilizing a binarization model by normalizing lighting of the sketch image, enhancing contrast of the sketch image, and converting the sketch image to a binary format. Further, the disclosed systems generate, utilizing one or more machine learning models, a digitized digital design of the sketch image based on the compositional reference. Moreover, the disclosed systems generating a layered digital design document comprising a background layer based on the digitized digital design and editable text elements based on the compositional reference.
A method, apparatus, non-transitory computer readable medium, and system for video generation includes obtaining an input prompt describing a scene. A video generation model generates a global token based on the input prompt by performing an attention process based on a plurality of frame tokens. The video generation model generates a frame token by performing an attention process based on the global token and a subset of the plurality of frame tokens in a local window. Subsequently, the video generation model generates a synthetic video based on the frame token, wherein the synthetic video depicts the scene and includes an image frame corresponding to the frame token.
An image processing system auto white balances an image using an object in the image and a reference color distribution. Given an input image, a target object in the input image is identified. A reference color distribution for the object type of the target object from the input image is accessed. One or more image processing settings are determined that, when applied to the input image, minimize a difference in values between pixels of the target object and the reference color distribution. A white balanced image is generated by applying the one or more image processing settings to the input image, and the white balanced image is provided for presentation.
Context-based prompt generation techniques for generative machine-learning models are described. In one or more examples, a user interface (UI) selection of a UI element of first digital content is received. A processing device captures contextual information associated with the UI selection. A machine-learning model generates a prompt based on the UI selection and the contextual information. Generative artificial intelligence (AI) generates second digital content based on the prompt. The generative AI is implemented using one or more machine-learning models. The processing device then presents the second digital content for display in a user interface.
G06F 16/338 - Présentation des résultats des requêtes
G06F 16/38 - Recherche caractérisée par l’utilisation de métadonnées, p. ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement
G06F 16/958 - Organisation ou gestion de contenu de sites Web, p. ex. publication, conservation de pages ou liens automatiques
Techniques for machine-learning material data generation are described. In an example, a processing device is operable to receive a digital image depicting a material and generate a set of video frames depicting physically-based rendering properties of the material. The set of video frames is generated based on the digital image using a video generative machine-learning model. The processing device is operable to output material data based on the physically-based rendering properties of the material depicted by the set of video frames.
Methods, computer systems, computer storage media, and graphical user interfaces are provided for facilitating content generation using target keywords for performance optimization. In one implementation, a set of search result rankings for a target website and one or more competitors of the target website in association with a set of keywords are obtained. Thereafter, candidate performant keywords are identified based on a comparison of search result rankings for the target website and search result rankings for the one or more competitors. The candidate performant keywords, or a portion thereof, are used to generated content data in association with the target website via one or more generative artificial intelligence (AI) models. Such content data can be presented via a display and/or incorporated into the target website.
G06F 40/14 - Documents en configuration arborescente
G06F 3/0481 - Techniques d’interaction fondées sur les interfaces utilisateur graphiques [GUI] fondées sur des propriétés spécifiques de l’objet d’interaction affiché ou sur un environnement basé sur les métaphores, p. ex. interaction avec des éléments du bureau telles les fenêtres ou les icônes, ou avec l’aide d’un curseur changeant de comportement ou d’aspect
G06F 16/2457 - Traitement des requêtes avec adaptation aux besoins de l’utilisateur
G06F 16/9538 - Présentation des résultats des requêtes
98.
DOCUMENT-RELATED QUERY ANSWERING USING A LANGUAGE GENERATION MODEL
A method, apparatus, non-transitory computer readable medium, and system for data processing includes receiving a document and a query requesting information about the document, identifying, using a language generation model, a relevant page of the document based on the query, and generating, using the language generation model, a response to the query based on the relevant page, wherein the response incudes the requested information about the document.
G06F 16/383 - Recherche caractérisée par l’utilisation de métadonnées, p. ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement utilisant des métadonnées provenant automatiquement du contenu
Machine-learning prompt enhancement techniques are described. In one or more examples, by generating training data from high-quality digital content meeting specific criteria, a generative artificial intelligence (AI) system is configurable to train an enhancement machine-learning model to capture features pertaining to particular tasks or scenarios. The trained enhancement machine-learning model can then extract enhancement features from inputs, enabling the formation of enhanced prompts that guide generative AI models to generate digital content as suitable for the particular tasks or scenarios.
Embodiments are disclosed for multi-color light-diffuser devices capable of displaying different colors based on stack configurations of polymer dispersed liquid crystal (PDLC) diffuser components, base layers, and filter layers. In one embodiment, a multi-color light-diffuser device can include a base layer positioned underneath a filter layer and a PDLC diffuser component positioned above the filter layer. In another embodiment, a multi-color light-diffuser can include an additional PDLC diffuser component in between the base layer and filter layer. The filter layer can be a dichroic material, a neutral density filter, or other transparent or semi-transparent material. The base layer can be an opaque material, such as paper, holographic film, iridescent film, or a mirror. Based on the activation of the light-scattering or non-light-scattering states of the PDLC diffuser components, the multi-color light-diffuser device can express different visual outputs based on the interactions/mixing of the filter layer and base layer.
G02F 1/1334 - Dispositions relatives à la structure basées sur des cristaux liquides dispersés dans un polymère, p. ex. cristaux liquides micro-encapsulés
G02F 1/1335 - Association structurelle de cellules avec des dispositifs optiques, p. ex. des polariseurs ou des réflecteurs
