SurfelSoup: Learned Point Cloud Geometry Compression With a Probablistic SurfelTree Representation

TL;DR

SurfelSoup introduces a learned, surface-structured point cloud compression method using a probabilistic hierarchical representation, achieving better compression and surface quality than existing voxel-based approaches.

Contribution

It proposes a novel probabilistic surfel-based hierarchy with adaptive tree termination for efficient point cloud geometry compression.

Findings

Outperforms voxel-based baselines in geometry compression

Provides smoother and more coherent surface reconstructions

Achieves consistent gains under MPEG test conditions

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.