3 papers
cs.CV2026
SURE: Semi-dense Uncertainty-REfined Feature Matching
Sicheng Li, Zaiwang Gu, Jie Zhang +3
Establishing reliable image correspondences is essential for many robotic vision problems. However, existing methods often struggle in challenging scenarios with large viewpoint ch…
cs.CV2025
GSCodec Studio: A Modular Framework for Gaussian Splat Compression
Sicheng Li, Chengzhen Wu, Hao Li +3
3D Gaussian Splatting and its extension to 4D dynamic scenes enable photorealistic, real-time rendering from real-world captures, positioning Gaussian Splats (GS) as a promising fo…
cs.CV2025
GIFStream: 4D Gaussian-based Immersive Video with Feature Stream
Hao Li, Sicheng Li, Xiang Gao +3
Immersive video offers a 6-Dof-free viewing experience, potentially playing a key role in future video technology. Recently, 4D Gaussian Splatting has gained attention as an effect…