5 papers · 1 filter
Learning a Delighting Prior for Facial Appearance Capture in the Wild
Yuxuan Han, Xin Ming, Tianxiao Li +4
High-quality facial appearance capture has traditionally required costly studio recording. Recent works consider an in-the-wild smartphone-based setup; however, their model-based i…
WildCap: Facial Albedo Capture in the Wild via Hybrid Inverse Rendering
Yuxuan Han, Xin Ming, Tianxiao Li +4
Existing methods achieve high-quality facial albedo capture under controllable lighting, which increases capture cost and limits usability. We propose WildCap, a novel method for h…
Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokens
Ziwei Shan, Yaoyu He, Chengfeng Zhao +5
Human bodily movements convey critical insights into action intentions and cognitive processes, yet existing multimodal systems primarily focused on understanding human motion via…
TANGLED: Generating 3D Hair Strands from Images with Arbitrary Styles and Viewpoints
Pengyu Long, Zijun Zhao, Min Ouyang +5
Hairstyles are intricate and culturally significant with various geometries, textures, and structures. Existing text or image-guided generation methods fail to handle the richness…
LLaVA-SLT: Visual Language Tuning for Sign Language Translation
Han Liang, Chengyu Huang, Yuecheng Xu +6
In the realm of Sign Language Translation (SLT), reliance on costly gloss-annotated datasets has posed a significant barrier. Recent advancements in gloss-free SLT methods have sho…