He Zhang

papers

999

total citations

papers (29)

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

CVPR 2025arXiv

citations

DoubleField: Bridging the Neural Surface and Radiance Fields for High-Fidelity Human Reconstruction and Rendering

CVPR 2022arXiv

citations

IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation

CVPR 2024arXiv

citations

Relightful Harmonization: Lighting-aware Portrait Background Replacement

CVPR 2024arXiv

citations

Semi-Supervised Parametric Real-World Image Harmonization

CVPR 2023arXiv

citations

Perceptual Artifacts Localization for Image Synthesis Tasks

ICCV 2023arXiv

citations

Boosting Robustness of Image Matting With Context Assembling and Strong Data Augmentation

CVPR 2022arXiv

citations

Controllable Shadow Generation Using Pixel Height Maps

ECCV 2022arXiv

citations

Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image

CVPR 2024arXiv

citations

PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing

CVPR 2023arXiv

citations

GOODAT: Towards Test-Time Graph Out-of-Distribution Detection

AAAI 2024arXiv

citations

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction

ICCV 2025arXiv

citations

MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors

CVPR 2024arXiv

citations

Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction

ICML 2024arXiv

citations

RD-Suite: A Benchmark for Ranking Distillation

NEURIPS 2023arXiv

citations

TransPixeler: Advancing Text-to-Video Generation with Transparency

CVPR 2025arXiv

citations

DIVE: Taming DINO for Subject-Driven Video Editing

ICCV 2025arXiv

citations

Text2Relight: Creative Portrait Relighting with Text Guidance

AAAI 2025arXiv

citations

Multitwine: Multi-Object Compositing with Text and Layout Control

CVPR 2025arXiv

citations

BiMark: Unbiased Multilayer Watermarking for Large Language Models

ICML 2025arXiv

citations

Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment

ICLR 2025arXiv

citations

MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond

CVPR 2025arXiv

citations

Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization

CVPR 2025arXiv

citations

Efficient Skill Discovery via Regret-Aware Optimization

ICML 2025arXiv

citations

LightPainter: Interactive Portrait Relighting With Freehand Scribble

CVPR 2023arXiv

citations

Co-evolution Transformer for Protein Contact Prediction

NEURIPS 2021

citations

He Zhang

papers (29)

Lite Vision Transformer With Enhanced Self-Attention

Mask Guided Matting via Progressive Refinement Network

SSH: A Self-Supervised Framework for Image Harmonization

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

DoubleField: Bridging the Neural Surface and Radiance Fields for High-Fidelity Human Reconstruction and Rendering

IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation

Relightful Harmonization: Lighting-aware Portrait Background Replacement

Semi-Supervised Parametric Real-World Image Harmonization

Perceptual Artifacts Localization for Image Synthesis Tasks

Boosting Robustness of Image Matting With Context Assembling and Strong Data Augmentation

Controllable Shadow Generation Using Pixel Height Maps

Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image

PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing

GOODAT: Towards Test-Time Graph Out-of-Distribution Detection

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction

MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors

Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction

RD-Suite: A Benchmark for Ranking Distillation

TransPixeler: Advancing Text-to-Video Generation with Transparency

DIVE: Taming DINO for Subject-Driven Video Editing

Text2Relight: Creative Portrait Relighting with Text Guidance

Multitwine: Multi-Object Compositing with Text and Layout Control

BiMark: Unbiased Multilayer Watermarking for Large Language Models

Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment

MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond

Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization

Efficient Skill Discovery via Regret-Aware Optimization

LightPainter: Interactive Portrait Relighting With Freehand Scribble

Co-evolution Transformer for Protein Contact Prediction

papers (29)

Lite Vision Transformer With Enhanced Self-Attention

Mask Guided Matting via Progressive Refinement Network

SSH: A Self-Supervised Framework for Image Harmonization

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

DoubleField: Bridging the Neural Surface and Radiance Fields for High-Fidelity Human Reconstruction and Rendering

IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation

Relightful Harmonization: Lighting-aware Portrait Background Replacement

Semi-Supervised Parametric Real-World Image Harmonization

Perceptual Artifacts Localization for Image Synthesis Tasks

Boosting Robustness of Image Matting With Context Assembling and Strong Data Augmentation

Controllable Shadow Generation Using Pixel Height Maps

Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image

PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing

GOODAT: Towards Test-Time Graph Out-of-Distribution Detection

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction

MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors

Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction

RD-Suite: A Benchmark for Ranking Distillation

TransPixeler: Advancing Text-to-Video Generation with Transparency

DIVE: Taming DINO for Subject-Driven Video Editing

Text2Relight: Creative Portrait Relighting with Text Guidance

Multitwine: Multi-Object Compositing with Text and Layout Control

BiMark: Unbiased Multilayer Watermarking for Large Language Models

Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment

MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond

Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization

Efficient Skill Discovery via Regret-Aware Optimization

LightPainter: Interactive Portrait Relighting With Freehand Scribble

Co-evolution Transformer for Protein Contact Prediction