MSC-Bench: Benchmarking and Analyzing Multi-Sensor Corruption for Driving Perception
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929654702538752 |
|---|---|
| author | Hao, Xiaoshuai Liu, Guanqun Zhao, Yuting Ji, Yuheng Wei, Mengchuan Zhao, Haimei Kong, Lingdong Yin, Rong Liu, Yu |
| author_facet | Hao, Xiaoshuai Liu, Guanqun Zhao, Yuting Ji, Yuheng Wei, Mengchuan Zhao, Haimei Kong, Lingdong Yin, Rong Liu, Yu |
| contents | Multi-sensor fusion models play a crucial role in autonomous driving perception, particularly in tasks like 3D object detection and HD map construction. These models provide essential and comprehensive static environmental information for autonomous driving systems. While camera-LiDAR fusion methods have shown promising results by integrating data from both modalities, they often depend on complete sensor inputs. This reliance can lead to low robustness and potential failures when sensors are corrupted or missing, raising significant safety concerns. To tackle this challenge, we introduce the Multi-Sensor Corruption Benchmark (MSC-Bench), the first comprehensive benchmark aimed at evaluating the robustness of multi-sensor autonomous driving perception models against various sensor corruptions. Our benchmark includes 16 combinations of corruption types that disrupt both camera and LiDAR inputs, either individually or concurrently. Extensive evaluations of six 3D object detection models and four HD map construction models reveal substantial performance degradation under adverse weather conditions and sensor failures, underscoring critical safety issues. The benchmark toolkit and affiliated code and model checkpoints have been made publicly accessible. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01037 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MSC-Bench: Benchmarking and Analyzing Multi-Sensor Corruption for Driving Perception Hao, Xiaoshuai Liu, Guanqun Zhao, Yuting Ji, Yuheng Wei, Mengchuan Zhao, Haimei Kong, Lingdong Yin, Rong Liu, Yu Robotics Artificial Intelligence Computer Vision and Pattern Recognition Multi-sensor fusion models play a crucial role in autonomous driving perception, particularly in tasks like 3D object detection and HD map construction. These models provide essential and comprehensive static environmental information for autonomous driving systems. While camera-LiDAR fusion methods have shown promising results by integrating data from both modalities, they often depend on complete sensor inputs. This reliance can lead to low robustness and potential failures when sensors are corrupted or missing, raising significant safety concerns. To tackle this challenge, we introduce the Multi-Sensor Corruption Benchmark (MSC-Bench), the first comprehensive benchmark aimed at evaluating the robustness of multi-sensor autonomous driving perception models against various sensor corruptions. Our benchmark includes 16 combinations of corruption types that disrupt both camera and LiDAR inputs, either individually or concurrently. Extensive evaluations of six 3D object detection models and four HD map construction models reveal substantial performance degradation under adverse weather conditions and sensor failures, underscoring critical safety issues. The benchmark toolkit and affiliated code and model checkpoints have been made publicly accessible. |
| title | MSC-Bench: Benchmarking and Analyzing Multi-Sensor Corruption for Driving Perception |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.01037 |