Learning-based lossless compression of 3D point cloud geometry

TL;DR

This paper introduces a novel learning-based lossless compression method for static 3D point cloud geometry that combines octree and voxel-based coding, utilizing neural networks to improve compression efficiency.

Contribution

It proposes a hybrid encoding approach that adaptively partitions point clouds and employs a deep neural network for probability modeling, outperforming existing standards.

Findings

Outperforms MPEG G-PCC with 28% average rate savings.

Uses a hybrid octree and voxel-based approach for better sparsity handling.

Employs a deep convolutional neural network for probability estimation.

Abstract

This paper presents a learning-based, lossless compression method for static point cloud geometry, based on context-adaptive arithmetic coding. Unlike most existing methods working in the octree domain, our encoder operates in a hybrid mode, mixing octree and voxel-based coding. We adaptively partition the point cloud into multi-resolution voxel blocks according to the point cloud structure, and use octree to signal the partitioning. On the one hand, octree representation can eliminate the sparsity in the point cloud. On the other hand, in the voxel domain, convolutions can be naturally expressed, and geometric information (i.e., planes, surfaces, etc.) is explicitly processed by a neural network. Our context model benefits from these properties and learns a probability distribution of the voxels using a deep convolutional neural network with masked filters, called VoxelDNN. Experiments show that our method outperforms the state-of-the-art MPEG G-PCC standard with average rate savings of 28% on a diverse set of point clouds from the Microsoft Voxelized Upper Bodies (MVUB) and MPEG. The implementation is available at https://github.com/Weafre/VoxelDNN.