AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Understanding the Robustness of 3D Object Detection With Bird's-Eye-View Representations in Autonomous Driving

Zijian Zhu, Yichi Zhang, Hai Chen, Yinpeng Dong, Shu Zhao, Wenbo Ding, Jiachen Zhong, Shibao Zheng

CVPR 2023 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use BEV representation (camera-only BEV models vs non-BEV)camera-only 3D detectors · ImageNet-C style common corruptions on nuScenes valmAP/NDSImproved
Adding camera-LiDAR fusion3D detectors · common corruptions and weather/lightingmAP/NDSImproved
Use BEV representation (BEV models vs non-BEV)camera-only 3D detectors · l_inf FGSM and PGD10 image perturbationsmAP/NDSHurt
Use Transformer blockscamera-only detectors · common corruptionsmAP/NDSImproved
Adding camera-LiDAR fusion (TransFusion/BEVFusion vs camera-only)3D detectors · l_inf FGSM attack on imagesNDS drop at eps=8: BEVFusion drops 10.0 vs 30.6 for BEVFormerImproved
Use BEV representation with temporal history (BEVFormer vs DETR3D)camera-only detectors · category-specific and temporally universal patch attacksNDS: BEVFormer outperforms DETR3D by at least 2.2 mAP and 5.8 NDS in temporally universal patch attackImproved
Use BEV representation (BEVDet/BEVDepth vs FCOS3D) under 3D consistent patchescamera-only detectors · instance-specific adversarial patchesmAP/NDSHurt
Increase input resolution from 704x256 to 1408x512 (ablation)BEVDet and BEVDepth · l_inf PGD10 attack on nuScenesNDS: BEVDepth eps=1 NDS 7.0 -> 11.0 (HighRes)Improved
Add temporal information (BEVDet -> BEVDet4D) (ablation)BEVDet · category-specific patch 5% and temporally universal patch 5%NDS: 15.4 -> 21.3 (category); 12.7 -> 17.5 (temporal)Improved
Add temporal history (BEVFormer vs BEVFormer-Static) (ablation)BEVFormer · category-specific patch 5% and temporally universal patch 5%NDS: 32.9 -> 35.9 (category); 30.3 -> 35.0 (temporal)Improved
Partial cameras: mask 3 non-adjacent cameras (lambda-mode vs Y-mode)camera-only detectors · nuScenes val partial camerasNDSMixed
Adding a fusion model component: BEVFusion vs TransFusion under point cloud perturbationfusion detectors · l_inf image and point cloud perturbationsrobustnessMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy