ParisLuco3D: A high-quality target dataset for domain generalization of LiDAR perception

TL;DR

ParisLuco3D is a new high-quality dataset designed for evaluating the domain generalization of LiDAR perception models across different environments and sensors, supporting benchmarking for segmentation, detection, and tracking.

Contribution

The paper introduces ParisLuco3D, a novel dataset with benchmarks for cross-domain LiDAR perception tasks, facilitating fair comparison and evaluation of models in diverse conditions.

Findings

Provides a comprehensive dataset for domain generalization evaluation.

Includes online benchmarks for segmentation, detection, and tracking.

Enables fair comparison of LiDAR perception methods across domains.

Abstract

LiDAR is an essential sensor for autonomous driving by collecting precise geometric information regarding a scene. %Exploiting this information for perception is interesting as the amount of available data increases. As the performance of various LiDAR perception tasks has improved, generalizations to new environments and sensors has emerged to test these optimized models in real-world conditions. This paper provides a novel dataset, ParisLuco3D, specifically designed for cross-domain evaluation to make it easier to evaluate the performance utilizing various source datasets. Alongside the dataset, online benchmarks for LiDAR semantic segmentation, LiDAR object detection, and LiDAR tracking are provided to ensure a fair comparison across methods. The ParisLuco3D dataset, evaluation scripts, and links to benchmarks can be found at the following website:https://npm3d.fr/parisluco3d