Learning to Predict on Octree for Scalable Point Cloud Geometry Coding
Authors:
- 1 August 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 96-102
Abstract
Octree-based point cloud representation and compression have been adopted by the MPEG G-PCC standard. However, it only uses handcrafted methods to predict the probability that a leaf node is non-empty, which is then used for entropy coding. We propose a novel approach for predicting such probabilities for geometry coding, which applies a denoising neural network to a “noisy” context cube that includes both neighboring decoded voxels as well as uncoded voxels. We further propose a convolution-based model to upsample the decoded point cloud at a coarse resolution on the decoder side. Integration of the two approaches significantly improves the rate-distortion performance for geometry coding compared to the original G-PCC standard and other baseline methods for dense point clouds. The proposed octree-based entropy coding approach is naturally scalable, which is desirable for dynamic rate adaptation in point cloud streaming systems.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Intra-Frame Context-Based Octree Coding for Point-Cloud Geometry2018
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection2018
- Performance assessment of point cloud compression2017
- Geometric distortion metrics for point cloud compression2017
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image DenoisingIEEE Transactions on Image Processing, 2017
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015
- Real-time compression of point cloud streams2012
- A Generic Scheme for Progressive Point Cloud CodingIEEE Transactions on Visualization and Computer Graphics, 2008
- Geometric compression for interactive transmission2000
- Geometric modeling using octree encodingComputer Graphics and Image Processing, 1982