Scott Cohen

SELECTIVELY REFINING AND RECOMBINING SEPARATE REGION MASKS FOR DISCONNECTED REGIONS OF A BASE MASK

GENERATING MULTIPLE SEGMENTATION MASKS IN A SINGLE MODEL WITH MULTI-TASK QUERY DECODERS

DETECTING SHADOWS AND CORRESPONDING OBJECTS IN DIGITAL IMAGES

DETECTING AND CORRECTING MISMATCHES BETWEEN IMAGES AND TEXT USING ASPECT-BASED VISION-LANGUAGE LEARNING

GENERATING MULTILINGUAL VISION LANGUAGE MODELS UTILIZING CONTRASTIVE LANGUAGE IMAGE PRETRAINING

JOINT FRAMEWORK FOR OBJECT-CENTERED SHADOW DETECTION, REMOVAL, AND SYNTHESIS

GENERATING AND MODIFYING DIGITAL IMAGE DATABASES THROUGH FAIRNESS DEDUPLICATION

GENERATING SYNTHETIC DIGITAL IMAGES UTILIZING A TEXT-TO-IMAGE GENERATION NEURAL NETWORK WITH LOCALIZED CONSTRAINTS

MODIFYING DIGITAL IMAGES VIA MULTI-LAYERED SCENE COMPLETION FACILITATED BY ARTIFICIAL INTELLIGENCE

MODIFYING DIGITAL IMAGES UTILIZING INTENT DETERMINISTIC USER INTERFACE TOOLS

DETECTING DIGITAL OBJECTS AND GENERATING OBJECT MASKS ON DEVICE

TRANSFERRING STYLES TO DIGITAL IMAGES IN AN OBJECT-AWARE MANNER

DIGITAL IMAGE INPAINTING UTILIZING GLOBAL AND LOCAL MODULATION LAYERS OF AN INPAINTING NEURAL NETWORK

EXTRACTING ATTRIBUTES FROM ARBITRARY DIGITAL IMAGES UTILIZING A MULTI-ATTRIBUTE CONTRASTIVE CLASSIFICATION NEURAL NETWORK

REMOVING DISTRACTING OBJECTS FROM DIGITAL IMAGES

DETECTING SHADOWS AND CORRESPONDING OBJECTS IN DIGITAL IMAGES

TEXTURE-PRESERVING SHADOW REMOVAL IN DIGITAL IMAGES UTILIZING GENERATING INPAINTING MODELS

SYNTHESIZING SHADOWS IN DIGITAL IMAGES UTILIZING DIFFUSION MODELS

MOVING OBJECTS CASTING A SHADOW AND GENERATING PORXY SHADOWS WITHIN A DIGITAL IMAGE

Modifying digital images via scene-based editing using image understanding facilitated by artificial intelligence

Detecting object relationships and editing digital images based on the object relationships

DILATING OBJECT MASKS TO REDUCE ARTIFACTS DURING INPAINTING

DETECTING AND MODIFYING OBJECT ATTRIBUTES

RECOVERING GAMUT COLOR LOSS UTILIZING LIGHTWEIGHT NEURAL NETWORKS

Modifying digital images utilizing intent deterministic user interface tools

MODIFYING DIGITAL IMAGES VIA PERSPECTIVE-AWARE OBJECT MOVE

MODIFYING DIGITAL IMAGES VIA DEPTH-AWARE OBJECT MOVE

MODIFYING DIGITAL IMAGES VIA MULTI-LAYERED SCENE COMPLETION FACILITATED BY ARTIFICIAL INTELLIGENCE

UTILIZING A GENERATIVE MACHINE LEARNING MODEL AND GRAPHICAL USER INTERFACE FOR CREATING MODIFIED DIGITAL IMAGES FROM AN INFILL SEMANTIC MAP

UTILIZING A GENERATIVE MACHINE LEARNING MODEL TO CREATE MODIFIED DIGITAL IMAGES FROM AN INFILL SEMANTIC MAP

LEARNING PARAMETERS FOR NEURAL NETWORKS USING A SEMANTIC DISCRIMINATOR AND AN OBJECT-LEVEL DISCRIMINATOR

ITERATIVELY MODIFYING INPAINTED DIGITAL IMAGES BASED ON CHANGES TO PANOPTIC SEGMENTATION MAPS

GENERATING AND PROVIDING A PANOPTIC INPAINTING INTERFACE FOR GENERATING AND MODIFYING INPAINTED DIGITAL IMAGES

PANOPTICALLY GUIDED INPAINTING UTILIZING A PANOPTIC INPAINTING NEURAL NETWORK

Applying object-aware style transfer to digital images

RETRIEVING DIGITAL IMAGES IN RESPONSE TO SEARCH QUERIES FOR SEARCH-DRIVEN IMAGE EDITING

Generating unified embeddings from multi-modal canvas inputs for image retrieval

OBJECT CLASS INPAINTING IN DIGITAL IMAGES UTILIZING CLASS-SPECIFIC INPAINTING NEURAL NETWORKS

Digital image inpainting utilizing a cascaded modulation inpainting neural network

GENERATING COMPOSITE IMAGES USING USER INTERFACE FEATURES FOR AUTO-COMPOSITING AND COMPOSITE-AWARE SEARCH

RECOMMENDING OBJECTS FOR IMAGE COMPOSITION USING GEOMETRY-AND-LIGHTING AWARE SEARCH AND EFFICIENT USER INTERFACE WORKFLOWS

RECOMMENDING OBJECTS FOR IMAGE COMPOSITION USING A GEOMETRY-AND-LIGHTING AWARE NEURAL NETWORK

Learning parameters for generative inpainting neural networks utilizing object-aware training and masked regularization

GENERATING DIGITAL IMAGES UTILIZING HIGH-RESOLUTION SPARSE ATTENTION AND SEMANTIC LAYOUT MANIPULATION NEURAL NETWORKS

Automatically detecting user-requested objects in digital images

METHODS AND SYSTEMS FOR GENERATING A SEMANTIC COMPUTATION GRAPH FOR UNDERSTANDING AND GROUNDING REFERRING EXPRESSIONS

UTILIZING INTERACTIVE DEEP LEARNING TO SELECT OBJECTS IN DIGITAL VISUAL MEDIA

Generating object masks of object parts utlizing deep learning

Detecting digital objects and generating object masks on device

Utilizing natural language processing automatically select objects in images

Utilizing deep neural networks to automatically select instances of detected objects in images

Extracting attributes from arbitrary digital images utilizing a multi-attribute contrastive classification neural network

Generating digital images utilizing high-resolution sparse attention and semantic layout manipulation neural networks

Determining colors of objects in digital images

Generating class-agnostic object masks in digital images

Segmenting objects using scale-diverse segmentation neural networks

Selecting instances of detected objects in images utilizing object detection models

Automatically selecting query objects in digital images

Flow-based color transfer from source graphic to target graphic

Utilizing natural language processing and multiple object detection models to automatically select objects in images

Interactive image matting using neural networks

Methods and systems for generating a semantic computation graph for understanding and grounding referring expressions

Neural networks for multi-label classification of sequential data

Flow-based color transfer from source graphic to target graphic

Classifying colors of objects in digital images

Utilizing object attribute detection models to automatically select instances of detected objects in images

Utilizing object attribute detection models to automatically select instances of detected objects in images

Automatically detecting user-requested objects in images

Image object segmentation based on temporal information

Image white balancing

Multi-module and multi-task machine learning system based on an ensemble of datasets

Interactive image matting using neural networks

Figure captioning system and related methods

Identifying target objects using scale-diverse segmentation neural networks

Image object segmentation based on temporal information

Recurrent neural network architectures which provide text describing images

Utilizing interactive deep learning to select objects in digital visual media

Image matting using deep learning

Question answering for data visualizations

Page segmentation of vector graphics documents

Utilizing interactive deep learning to select objects in digital visual media

Forecasting multiple poses based on a graphical image

Page segmentation of vector graphics documents

Forecasting multiple poses based on a graphical image

Planar region guided 3D geometry estimation from a single image

Recurrent neural network architectures which provide text describing images

Image matting using deep learning

Instance-level semantic segmentation system

Planar region guided 3D geometry estimation from a single image

Utilizing interactive deep learning to select objects in digital visual media

Image object segmentation using examples

Settings of a digital camera for depth map refinement

Depth map generation

Configuration settings of a digital camera for depth map generation

Settings of a digital camera for depth map refinement

Depth map generation

Labeling objects in image scenes

Semantic object proposal generation and validation

Semantic object selection