SurfelSoup: Learned Point Cloud Geometry Compression With a Probablistic SurfelTree Representation
Year: 2026
Type: preprint
Abstract: This paper presents SurfelSoup, an end-to-end learned surface-based framework for point cloud geometry compression, with surface-structured primitives for representation. It proposes a probabilistic surface representation, pSurfel, which models local point occupancies using a bounded generalized Gaussian distribution. In addition, the pSurfels are organized into an octree-like hierarchy, pSurfelTree, with a Tree Decision module that adaptively terminates the tree subdivision for rate-distortion optimal Surfel granularity selection. This formulation avoids redundant point-wise compression in smooth regions and produces compact yet smooth surface reconstructions. Experimental results under the MPEG common test condition show consistent gain on geometry compression over voxel-based baselines and MPEG standard G-PCC-GesTM-TriSoup, while providing visually superior reconstructions with smooth and coherent surface structures.
Source: arXiv (Cornell University)
Authors: Fan, Tingyu, Gong, Ran, Hu, Yueyu, Wang, Yao
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7127420329
Cites:
Cited by:
Related to: