3 papers
cs.CV2026
RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation
Yuhan Li, Fangao Zeng, Sicong Kang +5
Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequenti…
cs.CV2026
MuNet: A Mutualistic Network for Joint 3D Human Mesh Recovery and 3D Clothed Human Reconstruction from Single Images
Yunqi Gao, Leyuan Liu, Yuhan Li +2
3D human mesh recovery and 3D clothed human reconstruction are inherently related, yet they have long been studied in isolation, thereby overlooking the potential gains of joint op…
cs.CV2025
RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation
Xianfeng Tan, Yuhan Li, Wenxiang Shang +6
Standard clothing asset generation involves restoring forward-facing flat-lay garment images displayed on a clear background by extracting clothing information from diverse real-wo…