Improving Robustness of LiDAR-Camera Fusion Model against Weather Corruption from Fusion Strategy Perspective

TL;DR

This paper evaluates and improves the weather robustness of LiDAR-camera fusion models in autonomous driving by proposing a flexible fusion strategy that adapts to different weather conditions, validated across multiple models.

Contribution

It introduces a practical fusion strategy that enhances weather robustness of LiDAR-camera models, addressing a gap in robustness against weather-related corruption.

Findings

The proposed fusion strategy improves robustness across various weather conditions.

Experiments confirm broad applicability to different fusion models.

Enhanced models maintain performance under challenging weather scenarios.

Abstract

In recent years, LiDAR-camera fusion models have markedly advanced 3D object detection tasks in autonomous driving. However, their robustness against common weather corruption such as fog, rain, snow, and sunlight in the intricate physical world remains underexplored. In this paper, we evaluate the robustness of fusion models from the perspective of fusion strategies on the corrupted dataset. Based on the evaluation, we further propose a concise yet practical fusion strategy to enhance the robustness of the fusion models, namely flexibly weighted fusing features from LiDAR and camera sources to adapt to varying weather scenarios. Experiments conducted on four types of fusion models, each with two distinct lightweight implementations, confirm the broad applicability and effectiveness of the approach.