3 papers
cs.CV2026
UniCSG: Unified High-Fidelity Content-Constrained Style-Driven Generation via Staged Semantic and Frequency Disentanglement
Jingwei Yang, Ruoxi Wu, Wei Shen +4
Style transfer must match a target style while preserving content semantics. DiT-based diffusion models often suffer from content-style entanglement, leading to reference-content l…
cs.CV2025
RoleMotion: A Large-Scale Dataset towards Robust Scene-Specific Role-Playing Motion Synthesis with Fine-grained Descriptions
Junran Peng, Yiheng Huang, Silei Shen +8
In this paper, we introduce RoleMotion, a large-scale human motion dataset that encompasses a wealth of role-playing and functional motion data tailored to fit various specific sce…
cs.GR2025
SIG-Chat: Spatial Intent-Guided Conversational Gesture Generation Involving How, When and Where
Yiheng Huang, Junran Peng, Silei Shen +11
The accompanying actions and gestures in dialogue are often closely linked to interactions with the environment, such as looking toward the interlocutor or using gestures to point…