Geometric Prior Based Deep Human Point Cloud Geometry Compression

Xinju WU, Pingping ZHANG, Meng WANG, Peilin CHEN, Shiqi WANG, Sam KWONG

Research output: Journal PublicationsJournal Article (refereed)peer-review


The emergence of digital avatars has prompted an exponential increase in the demand for human point clouds with realistic and intricate details. The compression of such data becomes challenging due to massive amounts of data comprising millions of points. Herein, we leverage the human geometric prior in the geometry redundancy removal of point clouds to greatly promote compression performance. More specifically, the prior provides topological constraints as geometry initialization, allowing adaptive adjustments with a compact parameter set that can be represented with only a few bits. Therefore, we propose representing high-resolution human point clouds as a combination of a geometric prior and structural deviations. The prior is first derived with an aligned point cloud. Subsequently, the difference in features is compressed into a compact latent code. The proposed framework can operate in a plug-and-play fashion with existing learning-based point cloud compression methods. Extensive experimental results show that our approach significantly improves the compression performance without deteriorating the quality, demonstrating its promise in serving a variety of applications.
Original languageEnglish
Pages (from-to)1-1
JournalIEEE Transactions on Circuits and Systems for Video Technology
Publication statusE-pub ahead of print - 20 Mar 2024

Bibliographical note

Publisher Copyright:


  • Encoding
  • Feature extraction
  • Geometry
  • Octrees
  • Point cloud compression
  • Solid modeling
  • Three-dimensional displays
  • geometric prior
  • neural network


Dive into the research topics of 'Geometric Prior Based Deep Human Point Cloud Geometry Compression'. Together they form a unique fingerprint.

Cite this