Wenhao Chai

papers

962

total citations

papers (14)

Global Adaptation Meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation

ICCV 2023arXiv

citations

AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement

AAAI 2025arXiv

citations

RT-Pose: A 4D Radar-Tensor based 3D Human Pose Estimation and Localization Benchmark

ECCV 2024arXiv

citations

Science-T2I: Addressing Scientific Illusions in Image Synthesis

CVPR 2025arXiv

citations

UniAP: Towards Universal Animal Perception in Vision via Few-Shot Learning

AAAI 2024arXiv

citations

MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection

CVPR 2025arXiv

citations

Bringing RNNs Back to Efficient Open-Ended Video Understanding

ICCV 2025arXiv

citations

Zero-shot 3D Question Answering via Voxel-based Dynamic Token Compression

CVPR 2025

citations

PromptHaze: Prompting Real-world Dehazing via Depth Anything Model

AAAI 2025

citations

Wenhao Chai

papers (14)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

StableVideo: Text-driven Consistency-aware Diffusion Video Editing

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

Learning Diffusion Texture Priors for Image Restoration

PAD: Personalized Alignment of LLMs at Decoding-time

Global Adaptation Meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation

AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement

RT-Pose: A 4D Radar-Tensor based 3D Human Pose Estimation and Localization Benchmark

Science-T2I: Addressing Scientific Illusions in Image Synthesis

UniAP: Towards Universal Animal Perception in Vision via Few-Shot Learning

MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection

Bringing RNNs Back to Efficient Open-Ended Video Understanding

Zero-shot 3D Question Answering via Voxel-based Dynamic Token Compression

PromptHaze: Prompting Real-world Dehazing via Depth Anything Model

papers (14)

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

StableVideo: Text-driven Consistency-aware Diffusion Video Editing

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

Learning Diffusion Texture Priors for Image Restoration

PAD: Personalized Alignment of LLMs at Decoding-time

Global Adaptation Meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimation

AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement

RT-Pose: A 4D Radar-Tensor based 3D Human Pose Estimation and Localization Benchmark

Science-T2I: Addressing Scientific Illusions in Image Synthesis

UniAP: Towards Universal Animal Perception in Vision via Few-Shot Learning

MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection

Bringing RNNs Back to Efficient Open-Ended Video Understanding

Zero-shot 3D Question Answering via Voxel-based Dynamic Token Compression

PromptHaze: Prompting Real-world Dehazing via Depth Anything Model