Research map / Point clouds / Segmentation and detection
Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather
Martin Hahner, Christos Sakaridis, Dengxin Dai, Luc Van Gool
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 our physically based fog simulation to training | PV-RCNN · STF dense fog | mAP over classes (moderate): 37.51 -> 38.64 | Improved |
| add our fog simulation to training | PointRCNN · STF dense fog | mAP over classes (moderate): 35.47 -> 38.11 | Improved |
| add our fog simulation to training | SECOND · STF dense fog | mAP over classes (moderate): 34.52 -> 36.09 | Improved |
| add our fog simulation to training | Part-A2 · STF dense fog | mAP over classes (moderate): 34.34 -> 35.59 | Improved |
| add our fog simulation to training | PointPillars · STF dense fog | mAP over classes (moderate): 27.95 -> 30.68 | Improved |
| use our physical soft-target model instead of the heuristic prior fog simulation (ablation) | Part-A2 · STF dense fog | mAP over classes (moderate): 33.44 -> 35.59 | Improved |
| use our physical soft-target model instead of the heuristic prior fog simulation (ablation) | PointRCNN · STF dense fog | mAP over classes (moderate): 36.33 -> 38.11 | Improved |
| use our simulation instead of prior simulation (ablation) | PV-RCNN · STF dense fog | Car 3D AP@.5IoU (moderate): 46.60 -> 47.38 | Improved |
| add strongest-last filter at test time to clear-weather model (ablation) | PV-RCNN · STF dense fog | mAP over classes (moderate): 37.51 -> 37.98 | Improved |
| add strongest-last filter at test time to clear-weather model (ablation) | SECOND · STF dense fog | mAP over classes (moderate): 34.52 -> 34.43 | No clear effect |
| add strongest-last filter at test time to clear-weather model (ablation) | Part-A2 · STF dense fog | mAP over classes (moderate): 34.34 -> 34.25 | No clear effect |
| add our fog simulation to training | PointRCNN · STF dense fog Cyclist AP@.25IoU (moderate) | AP: 22.99 -> 22.88 | Hurt |
Closest papers by meaning
- Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection (AAAI 2024 · similarity 0.89)
- An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains (CVPR 2024 · similarity 0.87)
- L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection (AAAI 2025 · similarity 0.87)
- Equirectangular Point Reconstruction for Domain Adaptive Multimodal 3D Object Detection in Adverse Weather Conditions (AAAI 2025 · similarity 0.87)
- UAWTrack: Universal 3D Single Object Tracking in Adverse Weather (AAAI 2025 · similarity 0.86)
- GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection (CVPR 2025 · similarity 0.86)
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.
