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.
Cite
@article{arxiv.2602.00186,
title = {SurfelSoup: Learned Point Cloud Geometry Compression With a Probablistic SurfelTree Representation},
author = {Tingyu Fan and Ran Gong and Yueyu Hu and Yao Wang},
journal= {arXiv preprint arXiv:2602.00186},
year = {2026}
}