Relative Energy Learning for LiDAR Out-of-Distribution Detection

TL;DR

This paper introduces Relative Energy Learning (REL), a novel framework for LiDAR out-of-distribution detection that uses energy gaps and synthetic anomalies to improve safety in autonomous driving.

Contribution

REL leverages relative energy scores and a lightweight data synthesis method to enhance LiDAR OOD detection, outperforming existing approaches.

Findings

REL achieves superior detection accuracy on SemanticKITTI and STU benchmarks.

The relative energy approach reduces false positives and overconfidence in OOD detection.

Synthetic anomalies via Point Raise improve model robustness without real OOD data.

Abstract

Out-of-distribution (OOD) detection is a critical requirement for reliable autonomous driving, where safety depends on recognizing road obstacles and unexpected objects beyond the training distribution. Despite extensive research on OOD detection in 2D images, direct transfer to 3D LiDAR point clouds has been proven ineffective. Current LiDAR OOD methods struggle to distinguish rare anomalies from common classes, leading to high false-positive rates and overconfident errors in safety-critical settings. We propose Relative Energy Learning (REL), a simple yet effective framework for OOD detection in LiDAR point clouds. REL leverages the energy gap between positive (in-distribution) and negative logits as a relative scoring function, mitigating calibration issues in raw energy values and improving robustness across various scenes. To address the absence of OOD samples during training, we propose a lightweight data synthesis strategy called Point Raise, which perturbs existing point clouds to generate auxiliary anomalies without altering the inlier semantics. Evaluated on SemanticKITTI and the Spotting the Unexpected (STU) benchmark, REL consistently outperforms existing methods by a large margin. Our results highlight that modeling relative energy, combined with simple synthetic outliers, provides a principled and scalable solution for reliable OOD detection in open-world autonomous driving.