SB-BEVFusion: Enhancing the Robustness against Sensor Malfunction and Corruptions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Essl, Markus, Moscati, Marta, Noman, Mubashir, Zaheer, Muhammad Zaigham, Naseem, Usman, Nawaz, Shah, Schedl, Markus
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916004275159040
author Essl, Markus
Moscati, Marta
Noman, Mubashir
Zaheer, Muhammad Zaigham
Naseem, Usman
Nawaz, Shah
Schedl, Markus
author_facet Essl, Markus
Moscati, Marta
Noman, Mubashir
Zaheer, Muhammad Zaigham
Naseem, Usman
Nawaz, Shah
Schedl, Markus
contents Multimodal sensor fusion has demonstrated remarkable performance improvements over unimodal approaches in 3D object detection for autonomous vehicles. Typically, existing methods transform multimodal data from independent sensors, such as camera and LiDAR, into a unified bird's-eye view (BEV) representation for fusion. Although effective in ideal conditions, this strategy suffers from substantial performance deterioration when camera or LiDAR data are missing, corrupted, or noisy. To address this vulnerability, we develop a framework-agnostic fusion module for camera and LiDAR data that allows for handling cases when one of the two modalities is missing or corrupted. To demonstrate the effectiveness of our module, we instantiate it in BEVFusion [1], a well-established framework to combine camera and LiDAR data for 3D object detection. By means of quantitative experiments on the MultiCorrupt dataset, we demonstrate that our module achieves favorable performance improvements under scenarios of missing and corrupted modalities, substantially outperforming existing unified representation approaches across a wide range of sensor deterioration scenarios and reaching state-of-the-art performance in scenarios of corrupted modality due to extreme weather conditions and sensor failure.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11799
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SB-BEVFusion: Enhancing the Robustness against Sensor Malfunction and Corruptions
Essl, Markus
Moscati, Marta
Noman, Mubashir
Zaheer, Muhammad Zaigham
Naseem, Usman
Nawaz, Shah
Schedl, Markus
Computer Vision and Pattern Recognition
Multimodal sensor fusion has demonstrated remarkable performance improvements over unimodal approaches in 3D object detection for autonomous vehicles. Typically, existing methods transform multimodal data from independent sensors, such as camera and LiDAR, into a unified bird's-eye view (BEV) representation for fusion. Although effective in ideal conditions, this strategy suffers from substantial performance deterioration when camera or LiDAR data are missing, corrupted, or noisy. To address this vulnerability, we develop a framework-agnostic fusion module for camera and LiDAR data that allows for handling cases when one of the two modalities is missing or corrupted. To demonstrate the effectiveness of our module, we instantiate it in BEVFusion [1], a well-established framework to combine camera and LiDAR data for 3D object detection. By means of quantitative experiments on the MultiCorrupt dataset, we demonstrate that our module achieves favorable performance improvements under scenarios of missing and corrupted modalities, substantially outperforming existing unified representation approaches across a wide range of sensor deterioration scenarios and reaching state-of-the-art performance in scenarios of corrupted modality due to extreme weather conditions and sensor failure.
title SB-BEVFusion: Enhancing the Robustness against Sensor Malfunction and Corruptions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.11799