Krishna Kumar Singh

papers

630

total citations

papers (23)

Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

CVPR 2020arXiv

115

citations

GIRAFFE HD: A High-Resolution 3D-Aware Generative Model

CVPR 2022arXiv

108

citations

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation

CVPR 2020arXiv

citations

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization

ICCV 2025arXiv

citations

Contrastive Learning for Diverse Disentangled Foreground Generation

ECCV 2022arXiv

citations

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment

ECCV 2024arXiv

citations

Text2Relight: Creative Portrait Relighting with Text Guidance

AAAI 2025arXiv

citations

Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization

CVPR 2025arXiv

citations

Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data

NEURIPS 2020arXiv

citations

Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians

ICCV 2025arXiv

citations

UMFuse: Unified Multi View Fusion for Human Editing Applications

ICCV 2023arXiv

citations

Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks

ICCV 2025arXiv

citations

Complete 3D Human Reconstruction From a Single Incomplete Image

CVPR 2023

citations

Yo’Chameleon: Personalized Vision and Language Generation

CVPR 2025

citations

Krishna Kumar Singh

papers (23)

Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

GIRAFFE HD: A High-Resolution 3D-Aware Generative Model

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation

InsetGAN for Full-Body Image Generation

Putting People in Their Place: Affordance-Aware Human Insertion Into Scenes

Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing

Collaging Class-Specific GANs for Semantic Image Synthesis

IMAGINE: Image Synthesis by Image-Guided Model Inversion

UniHuman: A Unified Model For Editing Human Images in the Wild

ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models

X-Fusion: Introducing New Modality to Frozen Large Language Models

VGFlow: Visibility Guided Flow Network for Human Reposing

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization

Contrastive Learning for Diverse Disentangled Foreground Generation

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment

Text2Relight: Creative Portrait Relighting with Text Guidance

Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization

Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data

Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians

UMFuse: Unified Multi View Fusion for Human Editing Applications

Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks

Complete 3D Human Reconstruction From a Single Incomplete Image

Yo’Chameleon: Personalized Vision and Language Generation

papers (23)

Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

GIRAFFE HD: A High-Resolution 3D-Aware Generative Model

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation

InsetGAN for Full-Body Image Generation

Putting People in Their Place: Affordance-Aware Human Insertion Into Scenes

Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing

Collaging Class-Specific GANs for Semantic Image Synthesis

IMAGINE: Image Synthesis by Image-Guided Model Inversion

UniHuman: A Unified Model For Editing Human Images in the Wild

ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models

X-Fusion: Introducing New Modality to Frozen Large Language Models

VGFlow: Visibility Guided Flow Network for Human Reposing

DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization

Contrastive Learning for Diverse Disentangled Foreground Generation

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment

Text2Relight: Creative Portrait Relighting with Text Guidance

Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization

Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data

Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians

UMFuse: Unified Multi View Fusion for Human Editing Applications

Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks

Complete 3D Human Reconstruction From a Single Incomplete Image

Yo’Chameleon: Personalized Vision and Language Generation