Learning to Predict on Octree for Scalable Point Cloud Geometry Coding

TL;DR

This paper introduces a neural network-based method for predicting probabilities in octree-based point cloud compression, significantly enhancing rate-distortion performance and scalability for streaming applications.

Contribution

It presents a novel neural network approach for probability prediction in octree-based point cloud coding, improving compression efficiency and scalability.

Findings

Improved rate-distortion performance over G-PCC standard.

Enhanced scalability for dynamic point cloud streaming.

Effective neural network models for probability prediction and upsampling.

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.