SurfelSoup: Learned Point Cloud Geometry Compression With a Probablistic SurfelTree Representation
This work addresses the problem of efficient point cloud compression for applications like 3D graphics and virtual reality, offering an incremental improvement over existing methods.
The paper tackles point cloud geometry compression by introducing SurfelSoup, a learned surface-based framework that uses probabilistic surfels and an adaptive tree structure to achieve compact and smooth reconstructions. Experimental results show consistent gains over voxel-based baselines and the MPEG standard G-PCC-GesTM-TriSoup, with visually superior outcomes.
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.