Saved in:
Bibliographic Details
Main Authors: Zhang, Haifa, Wang, Yijing, Wang, Haoyu, Li, Zheng, Zuo, Zhiqiang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.30983
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910271851724800
author Zhang, Haifa
Wang, Yijing
Wang, Haoyu
Li, Zheng
Zuo, Zhiqiang
author_facet Zhang, Haifa
Wang, Yijing
Wang, Haoyu
Li, Zheng
Zuo, Zhiqiang
contents Despite the remarkable success of multi-modal bird's-eye view (BEV) perception in autonomous driving, current systems exhibit a critical vulnerability: existing fusion mechanisms are highly brittle to sensor corruptions, often causing catastrophic performance degradation. This vulnerability largely stems from the fact that standard fusion frameworks typically integrate multi-modal representations in a static manner, leading to a precipitous performance collapse under missing or corrupted modalities. In contrast, we show that graceful degradation is achievable through active modality reliability assessment. To this end, we present Grace-BEV, a lightweight and plug-and-play framework that enforces active reliability awareness during multi-modal fusion. Instead of relying on computationally expensive cross-modal interactions, Grace-BEV leverages the aligned BEV space to explicitly assess modality trustworthiness via a TrustGate Router and dynamically recalibrate feature integration using the FailSafe Fusion Block. Furthermore, we devise a Three-Phase Training strategy with Modality Dropout to prevent modality dominance and encourage balanced cross-modal learning under unreliable inputs. Extensive experiments on nuScenes-R and nuScenes-C show that Grace-BEV maintains robust performance across diverse corruption settings. Notably, under catastrophic LiDAR failures where standard baselines collapse to 0.0% mean Average Precision (mAP), Grace-BEV restores performance to as high as 34.7% mAP. Moreover, it improves clean accuracy by up to 1.4%, achieving a strong trade-off between robustness and efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30983
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Can BEV Perception Gracefully Degrade under Sensor Failures?
Zhang, Haifa
Wang, Yijing
Wang, Haoyu
Li, Zheng
Zuo, Zhiqiang
Computer Vision and Pattern Recognition
Despite the remarkable success of multi-modal bird's-eye view (BEV) perception in autonomous driving, current systems exhibit a critical vulnerability: existing fusion mechanisms are highly brittle to sensor corruptions, often causing catastrophic performance degradation. This vulnerability largely stems from the fact that standard fusion frameworks typically integrate multi-modal representations in a static manner, leading to a precipitous performance collapse under missing or corrupted modalities. In contrast, we show that graceful degradation is achievable through active modality reliability assessment. To this end, we present Grace-BEV, a lightweight and plug-and-play framework that enforces active reliability awareness during multi-modal fusion. Instead of relying on computationally expensive cross-modal interactions, Grace-BEV leverages the aligned BEV space to explicitly assess modality trustworthiness via a TrustGate Router and dynamically recalibrate feature integration using the FailSafe Fusion Block. Furthermore, we devise a Three-Phase Training strategy with Modality Dropout to prevent modality dominance and encourage balanced cross-modal learning under unreliable inputs. Extensive experiments on nuScenes-R and nuScenes-C show that Grace-BEV maintains robust performance across diverse corruption settings. Notably, under catastrophic LiDAR failures where standard baselines collapse to 0.0% mean Average Precision (mAP), Grace-BEV restores performance to as high as 34.7% mAP. Moreover, it improves clean accuracy by up to 1.4%, achieving a strong trade-off between robustness and efficiency.
title Can BEV Perception Gracefully Degrade under Sensor Failures?
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.30983