Compression of Large-Scale 3D Point Clouds Based on Joint Optimization of Point Sampling and Feature Extraction
This addresses storage and transmission challenges for LiDAR data in applications like autonomous driving, representing an incremental improvement over existing methods.
The paper tackles the problem of compressing large-scale 3D point clouds by proposing a fully end-to-end training framework that jointly optimizes point sampling and feature extraction, achieving significantly higher compression ratios on datasets like SemanticKITTI and nuScenes.
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.