3 papers
eess.IV2026
SurfelSoup: Learned Point Cloud Geometry Compression With a Probablistic SurfelTree Representation
Tingyu Fan, Ran Gong, Yueyu Hu +1
This paper presents SurfelSoup, an end-to-end learned surface-based framework for point cloud geometry compression, with surface-structured primitives for representation. It propos…
cs.CV2025
TeSO: Representing and Compressing 3D Point Cloud Scenes with Textured Surfel Octree
Yueyu Hu, Ran Gong, Tingyu Fan +1
3D visual content streaming is a key technology for emerging 3D telepresence and AR/VR applications. One fundamental element underlying the technology is a versatile 3D representat…
cs.CV2025
U-Motion: Learned Point Cloud Video Compression with U-Structured Temporal Context Generation
Tingyu Fan, Yueyu Hu, Ran Gong +1
Point cloud video (PCV) is a versatile 3D representation of dynamic scenes with emerging applications. This paper introduces U-Motion, a learning-based compression scheme for both…