Research map / 3D vision / 3D generation
Benchmarking and Improving Bird’s Eye View Perception Robustness in Autonomous Driving
Shaoyuan Xie, Lingdong Kong, Wenwei Zhang, Jiawei Ren, Liang Pan, Kai Chen, Ziwei Liu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add corruption augmentation (ablation) | BEVFormer · nuScenes-C | mRR: 0.6040 -> 0.7427 | Improved |
| add corruption augmentation (ablation) | PETR · nuScenes-C | mRR: 0.6503 -> 0.8555 | Improved |
| add corruption augmentation (ablation) | BEVDet · nuScenes-C | clean NDS: 0.3500 -> 0.3326 | Hurt |
| add corruption augmentation (ablation) | FCOS3D · day-to-night | NDS: 0.0854 -> 0.1245 | Improved |
| add corruption augmentation (ablation) | FCOS3D · dry-to-rain | NDS: 0.3203 -> 0.3302 | Improved |
| add corruption augmentation for sensor failure (ablation) | BEV detectors · Camera Crash | NDS: 0.3154 -> 0.3267 | No clear effect |
| freeze CLIP backbone instead of baseline backbone (ablation) | BEVDet · nuScenes-C | mRR: 58.54 -> 52.61 | Hurt |
| end-to-end fine-tune CLIP with random head (ablation) | BEVDet · nuScenes-C | mRR: 58.54 -> 59.10 | No clear effect |
| add head alignment stage before fine-tuning CLIP (ablation) | BEVDet · nuScenes-C | mRR: 59.10 -> 61.18 | Improved |
| add head alignment plus corruption augmentation to CLIP (ablation) | BEVDet · nuScenes-C | mRR: 80.84 -> 84.32 | Improved |
| add M-BEV masked pre-training (ablation) | PETR · Camera Crash | NDS: 0.2347 -> 0.2759 | Improved |
| add FCOS3D pre-training (ablation) | BEVDet (r101) · nuScenes-C | clean NDS: 0.3877 -> 0.3780 | Mixed |
Closest papers by meaning
- A Black-Box Evaluation Framework for Semantic Robustness in Bird’s Eye View Detection (AAAI 2025 · similarity 0.92)
- M-BEV: Masked BEV Perception for Robust Autonomous Driving (AAAI 2024 · similarity 0.91)
- Improving Bird's Eye View Semantic Segmentation by Task Decomposition (CVPR 2024 · similarity 0.90)
- Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting (CVPR 2025 · similarity 0.90)
- MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations (ICLR 2025 · similarity 0.88)
- Predictive Uncertainty Quantification for Bird's Eye View Segmentation: A Benchmark and Novel Loss Function (ICLR 2025 · similarity 0.87)
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.
