Learning to Identify Out-of-Distribution Objects for 3D LiDAR Anomaly Segmentation

TL;DR

This paper presents a novel feature-space approach for 3D LiDAR anomaly segmentation in autonomous driving, introducing new datasets and achieving state-of-the-art results.

Contribution

It introduces a direct feature-space method for 3D LiDAR anomaly detection and creates mixed real-synthetic datasets to improve domain generalization.

Findings

Achieves state-of-the-art results on real-world datasets.

Demonstrates effectiveness of mixed datasets in bridging domain gaps.

Validates approach through extensive experiments.

Abstract

Understanding the surrounding environment is fundamental in autonomous driving and robotic perception. Distinguishing between known classes and previously unseen objects is crucial in real-world environments, as done in Anomaly Segmentation. However, research in the 3D field remains limited, with most existing approaches applying post-processing techniques from 2D vision. To cover this lack, we propose a new efficient approach that directly operates in the feature space, modeling the feature distribution of inlier classes to constrain anomalous samples. Moreover, the only publicly available 3D LiDAR anomaly segmentation dataset contains simple scenarios, with few anomaly instances, and exhibits a severe domain gap due to its sensor resolution. To bridge this gap, we introduce a set of mixed real-synthetic datasets for 3D LiDAR anomaly segmentation, built upon established semantic segmentation benchmarks, with multiple out-of-distribution objects and diverse, complex environments. Extensive experiments demonstrate that our approach achieves state-of-the-art and competitive results on the existing real-world dataset and the newly introduced mixed datasets, respectively, validating the effectiveness of our method and the utility of the proposed datasets. Code and datasets are available at https://simom0.github.io/lido-page/.