Compression of Large-Scale 3D Point Clouds Based on Joint Optimization of Point Sampling and Feature Extraction

TL;DR

This paper introduces an end-to-end trainable framework for compressing large-scale 3D point clouds by jointly optimizing point sampling and feature extraction, resulting in higher compression ratios.

Contribution

It presents a novel joint optimization approach for point sampling and feature extraction in 3D point cloud compression, improving over existing separate methods.

Findings

Achieves higher compression ratios than state-of-the-art methods.

Demonstrates effectiveness on SemanticKITTI and nuScenes datasets.

Provides a trainable point sampling and adaptive reconstruction scheme.

Abstract

Large-scale 3D point clouds (LS3DPC) obtained by LiDAR scanners require huge storage space and transmission bandwidth due to a large amount of data. The existing methods of LS3DPC compression separately perform rule-based point sampling and learnable feature extraction, and hence achieve limited compression performance. In this paper, we propose a fully end-to-end training framework for LS3DPC compression where the point sampling and the feature extraction are jointly optimized in terms of the rate and distortion losses. To this end, we first make the point sampling module to be trainable such that an optimal position of the downsampled point is estimated via aggregation with learnable weights. We also develop a reliable point reconstruction scheme that adaptively aggregates the expanded candidate points to refine the positions of upsampled points. Experimental results evaluated on the SemanticKITTI and nuScenes datasets show that the proposed method achieves significantly higher compression ratios compared with the existing state-of-the-art methods.