Weihua Chen

8

Papers

56

Total Citations

Papers (8)

Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation

Exploring More from Multiple Gait Modalities for Human Identification

FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion

RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images

On Denoising Walking Videos for Gait Recognition

CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step

Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation

RealisID: Scale-Robust and Fine-Controllable Identity Customization via Local and Global Complementation