Krishna Kumar Singh

SYSTEMS AND METHODS FOR RELIGHTED IMAGE GENERATION

EDITING IMAGES WITH AN IMAGE GENERATION MODEL

GENERATING THREE-DIMENSIONAL HUMAN MODELS REPRESENTING TWO-DIMENSIONAL HUMANS IN TWO-DIMENSIONAL IMAGES

REMOVING DISTRIBUTIONAL DISCREPANCIES IN CAPTIONS FOR IMAGE-TEXT ALIGNMENT

GENERATIVE PORTRAIT SHADOW REMOVAL

MEAN-SHIFT NORMALIZATION FOR IMAGE PROCESSING

SUBJECT-AWARE VIDEO BACKGROUND GENERATION

SYSTEMS AND METHODS FOR GENERATING A RELIGHTED IMAGE

CONDITION-BASED IMAGE EDITING

PROXY-GUIDED IMAGE EDITING

GROUP PORTRAIT PHOTO EDITING

UTILIZING MACHINE LEARNING MODELS TO GENERATE IMAGE EDITING DIRECTIONS IN A LATENT SPACE

HUMAN INPAINTING UTILIZING A SEGMENTATION BRANCH FOR GENERATING AN INFILL SEGMENTATION MAP

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

DISCOVERING AND MITIGATING BIASES IN LARGE PRE-TRAINED MULTIMODAL BASED IMAGE EDITING

GENERATING A MODIFIED DIGITAL IMAGE UTILIZING A HUMAN INPAINTING MODEL

IMAGE AND DEPTH MAP GENERATION USING A CONDITIONAL MACHINE LEARNING

COMPLETE 3D OBJECT RECONSTRUCTION FROM AN INCOMPLETE IMAGE

CONTROLLABLE DIFFUSION MODEL

UTILIZING INDIVIDUAL-CONCEPT TEXT-IMAGE ALIGNMENT TO ENHANCE COMPOSITIONAL CAPACITY OF TEXT-TO-IMAGE MODELS

IMAGE INPAINTING USING A CONTENT PRESERVATION VALUE

GAN IMAGE GENERATION FROM FEATURE REGULARIZATION

MIX AND MATCH HUMAN IMAGE GENERATION

DIGITAL IMAGE REPOSING BASED ON MULTIPLE INPUT VIEWS

DIGITAL IMAGE REPOSING TECHNIQUES

GENERATIVE IMAGE FILLING USING A REFERENCE IMAGE

IMAGE GENERATION WITH MULTIPLE IMAGE EDITING MODES

UTILIZING REGULARIZED FORWARD DIFFUSION FOR IMPROVED INVERSION OF DIGITAL IMAGES

UTILIZING CROSS-ATTENTION GUIDANCE TO PRESERVE CONTENT IN DIFFUSION-BASED IMAGE MODIFICATIONS

ONE-CLICK IMAGE EXTENSION WITH QUICK MASK ADJUSTMENT

UTILIZING MACHINE LEARNING MODELS TO GENERATE IMAGE EDITING DIRECTIONS IN A LATENT SPACE

MULTIMODAL DIFFUSION MODELS

GENERATIVE MODEL FOR MULTI-MODALITY OUTPUTS FROM A SINGLE INPUT

AFFORDANCE-BASED REPOSING OF AN OBJECT IN A SCENE

MODIFYING POSES OF TWO-DIMENSIONAL HUMANS IN TWO-DIMENSIONAL IMAGES BY REPOSING THREE-DIMENSIONAL HUMAN MODELS REPRESENTING THE TWO-DIMENSIONAL HUMANS

GENERATING THREE-DIMENSIONAL HUMAN MODELS REPRESENTING TWO-DIMENSIONAL HUMANS IN TWO-DIMENSIONAL IMAGES

GENERATIVE MODEL FOR MULTI-MODALITY OUTPUTS FROM A SINGLE INPUT

SYNTHESIZING A MODIFIED DIGITAL IMAGE UTILIZING A REPOSING MODEL

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

UTILIZING A WARPED DIGITAL IMAGE WITH A REPOSING MODEL TO SYNTHESIZE A MODIFIED DIGITAL IMAGE

HUMAN INPAINTING UTILIZING A SEGMENTATION BRANCH FOR GENERATING AN INFILL SEGMENTATION MAP

Generating a modified digital image utilizing a human inpainting model

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

DEBIASING IMAGE TO IMAGE TRANSLATION MODELS

Diverse image inpainting using contrastive learning

Image inversion using multiple latent spaces

Generating animated digital videos utilizing a character animation neural network informed by pose and motion embeddings

Generating simulated images that enhance socio-demographic diversity

Generating synthesized digital images utilizing a multi-resolution generator neural network

Generating synthesized digital images utilizing class-specific machine-learning models

Synthesizing digital images utilizing image-guided model inversion of an image classifier