Kaihao Zhang

papers

1,836

total citations

papers (24)

Single Image Super-Resolution via a Holistic Attention Network

ECCV 2020arXiv

777

citations

Deblurring by Realistic Blurring

CVPR 2020arXiv

440

citations

MB-TaylorFormer: Multi-Branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing

ICCV 2023arXiv

193

citations

TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation

NEURIPS 2020arXiv

156

citations

ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring

CVPR 2021arXiv

citations

Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation

NEURIPS 2020arXiv

citations

Deep Two-View Structure-From-Motion Revisited

CVPR 2021arXiv

citations

MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion

ICCV 2025arXiv

citations

Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling

ICLR 2025arXiv

citations

Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models

NEURIPS 2023

citations

Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding

ECCV 2020

citations

Benchmarking Ultra-High-Definition Image Super-Resolution

ICCV 2021

citations

Pyramid Architecture Search for Real-Time Image Deblurring

ICCV 2021

citations

Robust Single Image Reflection Removal Against Adversarial Attacks

CVPR 2023

citations

F&F Attack: Adversarial Attack against Multiple Object Trackers by Inducing False Negatives and False Positives

ICCV 2023

citations

MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration

ICCV 2025

citations

Cross-View Isolated Sign Language Recognition via View Synthesis and Feature Disentanglement

ICCV 2025

citations

LDPose: Towards Inclusive Human Pose Estimation for Limb-Deficient Individuals in the Wild

ICCV 2025

citations

View From Above: Orthogonal-View aware Cross-view Localization

CVPR 2024

citations

Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency

NEURIPS 2020

citations

Unsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identification

ECCV 2020

citations

Kaihao Zhang

papers (24)

Single Image Super-Resolution via a Holistic Attention Network

Deblurring by Realistic Blurring

MB-TaylorFormer: Multi-Branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing

TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation

ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring

Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation

Deep Two-View Structure-From-Motion Revisited

MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion

Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling

Homography Guided Temporal Fusion for Road Line and Marking Segmentation

Prompting Future Driven Diffusion Model for Hand Motion Prediction

Model Calibration in Dense Classification with Adaptive Label Perturbation

Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models

Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding

Benchmarking Ultra-High-Definition Image Super-Resolution

Pyramid Architecture Search for Real-Time Image Deblurring

Robust Single Image Reflection Removal Against Adversarial Attacks

F&F Attack: Adversarial Attack against Multiple Object Trackers by Inducing False Negatives and False Positives

MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration

Cross-View Isolated Sign Language Recognition via View Synthesis and Feature Disentanglement

LDPose: Towards Inclusive Human Pose Estimation for Limb-Deficient Individuals in the Wild

View From Above: Orthogonal-View aware Cross-view Localization

Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency

Unsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identification

papers (24)

Single Image Super-Resolution via a Holistic Attention Network

Deblurring by Realistic Blurring

MB-TaylorFormer: Multi-Branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing

TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation

ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring

Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation

Deep Two-View Structure-From-Motion Revisited

MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion

Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling

Homography Guided Temporal Fusion for Road Line and Marking Segmentation

Prompting Future Driven Diffusion Model for Hand Motion Prediction

Model Calibration in Dense Classification with Adaptive Label Perturbation

Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models

Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding

Benchmarking Ultra-High-Definition Image Super-Resolution

Pyramid Architecture Search for Real-Time Image Deblurring

Robust Single Image Reflection Removal Against Adversarial Attacks

F&F Attack: Adversarial Attack against Multiple Object Trackers by Inducing False Negatives and False Positives

MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration

Cross-View Isolated Sign Language Recognition via View Synthesis and Feature Disentanglement

LDPose: Towards Inclusive Human Pose Estimation for Limb-Deficient Individuals in the Wild

View From Above: Orthogonal-View aware Cross-view Localization

Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency

Unsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identification