8 papers
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…
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…
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…
Spatial Visibility and Temporal Dynamics: Revolutionizing Field of View Prediction in Adaptive Point Cloud Video Streaming
Chen Li, Tongyu Zong, Yueyu Hu +2
Field-of-View (FoV) adaptive streaming significantly reduces bandwidth requirement of immersive point cloud video (PCV) by only transmitting visible points in a viewer's FoV. The t…
Bits-to-Photon: End-to-End Learned Scalable Point Cloud Compression for Direct Rendering
Yueyu Hu, Ran Gong, Yao Wang
Point cloud is a promising 3D representation for volumetric streaming in emerging AR/VR applications. Despite recent advances in point cloud compression, decoding and rendering hig…
Low Latency Point Cloud Rendering with Learned Splatting
Yueyu Hu, Ran Gong, Qi Sun +1
Point cloud is a critical 3D representation with many emerging applications. Because of the point sparsity and irregularity, high-quality rendering of point clouds is challenging a…