Multiscale Latent-Guided Entropy Model for LiDAR Point Cloud Compression

TL;DR

This paper introduces a novel multiscale, hierarchical deep learning framework for LiDAR point cloud compression that significantly improves efficiency and achieves state-of-the-art performance, reducing decoding time by over 99.8%.

Contribution

It proposes a fully-factorized, end-to-end deep model with hierarchical latent variables and residual coding for efficient, parallelizable LiDAR point cloud compression.

Findings

Achieves state-of-the-art compression performance on SemanticKITTI and Ford datasets.

Reduces decoding time by more than 99.8% compared to previous methods.

Demonstrates high parallelization and time efficiency of the proposed framework.

Abstract

The non-uniform distribution and extremely sparse nature of the LiDAR point cloud (LPC) bring significant challenges to its high-efficient compression. This paper proposes a novel end-to-end, fully-factorized deep framework that encodes the original LPC into an octree structure and hierarchically decomposes the octree entropy model in layers. The proposed framework utilizes a hierarchical latent variable as side information to encapsulate the sibling and ancestor dependence, which provides sufficient context information for the modelling of point cloud distribution while enabling the parallel encoding and decoding of octree nodes in the same layer. Besides, we propose a residual coding framework for the compression of the latent variable, which explores the spatial correlation of each layer by progressive downsampling, and model the corresponding residual with a fully-factorized entropy model. Furthermore, we propose soft addition and subtraction for residual coding to improve network flexibility. The comprehensive experiment results on the LiDAR benchmark SemanticKITTI and MPEG-specified dataset Ford demonstrates that our proposed framework achieves state-of-the-art performance among all the previous LPC frameworks. Besides, our end-to-end, fully-factorized framework is proved by experiment to be high-parallelized and time-efficient and saves more than 99.8% of decoding time compared to previous state-of-the-art methods on LPC compression.