Improved Deep Point Cloud Geometry Compression

  title={Improved Deep Point Cloud Geometry Compression},
  author={Maurice Quach and G. Valenzise and F. Dufaux},
  journal={2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)},
  • Maurice Quach, G. Valenzise, F. Dufaux
  • Published 2020
  • Computer Science, Engineering, Mathematics
  • 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)
Point clouds have been recognized as a crucial data structure for 3D content and are essential in a number of applications such as virtual and mixed reality, autonomous driving, cultural heritage, etc. In this paper, we propose a set of contributions to improve deep point cloud compression, i.e.: using a scale hyperprior model for entropy coding; employing deeper transforms; a different balancing weight in the focal loss; optimal thresholding for decoding; and sequential model training. In… Expand
DeepCompress: Efficient Point Cloud Geometry Compression
A deep perceptual metric for 3D point clouds
Adaptive Deep Learning-Based Point Cloud Geometry Coding
Towards neural network approaches for point cloud compression
Deep Compression for Dense Point Cloud Maps
GROOT: a real-time streaming system of high-fidelity volumetric videos


Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression
Adaptive Multi-level Triangle Soup for Geometry-based Point Cloud Coding
  • Antoine Dricot, J. Ascenso
  • Computer Science
  • 2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP)
  • 2019
Deep Learning-Based Point Cloud Coding: A Behavior and Performance Study
Hybrid Octree-Plane Point Cloud Geometry Coding
Graph-Based Static 3D Point Clouds Geometry Coding
Intra-Frame Context-Based Octree Coding for Point-Cloud Geometry
Octree-based Point-Cloud Compression
Geometric distortion metrics for point cloud compression
Emerging MPEG Standards for Point Cloud Compression
A Volumetric Approach to Point Cloud Compression