Neural Network Modeling of Probabilities for Coding the Octree Representation of Point Clouds

TL;DR

This paper introduces a neural network-based lossless point cloud compression method that models voxel occupancy probabilities within an octree structure, achieving state-of-the-art results through context-aware probability estimation.

Contribution

It presents a novel neural network approach for estimating voxel occupancy probabilities in octree-based point cloud compression, with fast and slow variants for improved efficiency.

Findings

Achieves state-of-the-art compression performance on benchmark datasets.

Introduces a neural network model that uses 3D context for probability estimation.

Provides a fast version enabling higher parallelization during encoding and decoding.

Abstract

This paper describes a novel lossless point cloud compression algorithm that uses a neural network for estimating the coding probabilities for the occupancy status of voxels, depending on wide three dimensional contexts around the voxel to be encoded. The point cloud is represented as an octree, with each resolution layer being sequentially encoded and decoded using arithmetic coding, starting from the lowest resolution, until the final resolution is reached. The occupancy probability of each voxel of the splitting pattern at each node of the octree is modeled by a neural network, having at its input the already encoded occupancy status of several octree nodes (belonging to the past and current resolutions), corresponding to a 3D context surrounding the node to be encoded. The algorithm has a fast and a slow version, the fast version selecting differently several voxels of the context, which allows an increased parallelization by sending larger batches of templates to be estimated by the neural network, at both encoder and decoder. The proposed algorithms yield state-of-the-art results on benchmark datasets. The implementation will be made available at https://github.com/marmus12/nnctx