Poster: Making Edge-assisted LiDAR Perceptions Robust to Lossy Point Cloud Compression

TL;DR

This paper introduces an interpolation algorithm that enhances the quality of lossy compressed LiDAR point clouds, aiming to maintain perception accuracy in resource-constrained edge computing scenarios.

Contribution

It proposes a novel interpolation method for range images that improves point cloud quality after lossy compression, aiding robust edge-assisted LiDAR perception.

Findings

Better qualitative reconstruction of point clouds from interpolated range images

Improved perception performance despite lossy compression

Preliminary results show promising enhancement in data quality

Abstract

Real-time light detection and ranging (LiDAR) perceptions, e.g., 3D object detection and simultaneous localization and mapping are computationally intensive to mobile devices of limited resources and often offloaded on the edge. Offloading LiDAR perceptions requires compressing the raw sensor data, and lossy compression is used for efficiently reducing the data volume. Lossy compression degrades the quality of LiDAR point clouds, and the perception performance is decreased consequently. In this work, we present an interpolation algorithm improving the quality of a LiDAR point cloud to mitigate the perception performance loss due to lossy compression. The algorithm targets the range image (RI) representation of a point cloud and interpolates points at the RI based on depth gradients. Compared to existing image interpolation algorithms, our algorithm shows a better qualitative result when the point cloud is reconstructed from the interpolated RI. With the preliminary results, we also describe the next steps of the current work.