Research map / Point clouds / Segmentation and detection
Weather-Robust LiDAR Perception: Point Cloud Restoration from Adverse Weather
Chenghao Sun, Pengpeng Sun, Xiangmo Zhao
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 spatial-frequency block (ablation) | LTDNet (PE only) · IQA3D, PV-RCNN | AP: 40.2 -> 42.4 | Improved |
| add probabilistic pruning block (ablation) | LTDNet (PE+SFB) · IQA3D, PV-RCNN | AP: 42.4 -> 43.1 | Improved |
| add weather-aware block (ablation) | LTDNet (PE+SFB+PPB) · IQA3D, PV-RCNN | AP: 43.1 -> 43.6 | Improved |
| preprocess degraded LiDAR with LTDNet | PV-RCNN · RADIATE-W Rain (0-80m) | AP@0.5: 38.43 -> 43.25 | Improved |
| preprocess degraded LiDAR with LTDNet | PV-RCNN · RADIATE-W Snow (0-80m) | AP@0.5: 36.53 -> 41.76 | Improved |
| preprocess with LTDNet | PointPillars · RADIATE-W Fog (0-80m) | AP@0.5: 29.19 -> 33.12 | Improved |
| preprocess with LTDNet | CenterPoint · RADIATE-W Rain (0-80m) | AP@0.5: 38.54 -> 42.87 | Improved |
| preprocess with denoising baselines (DSOR, 4DenoiseNet, 3D-UnOutDet) | 3D detectors · RADIATE-W/DENSE-W | AP@0.5: typically less than 2 AP | No clear effect |
| use LTDNet instead of denoising baselines | point cloud quality · RADIATE/DENSE degraded scans | DDI: baselines around 0.30; LTDNet 0.61 to 0.81 | Improved |
| denoising-only methods vs LTDNet on noise removal | point cloud quality · RADIATE/DENSE | NR-F1: all about 90% | No clear effect |
Closest papers by meaning
- An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains (CVPR 2024 · similarity 0.88)
- L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection (AAAI 2025 · similarity 0.87)
- WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusion (CVPR 2025 · similarity 0.87)
- Equirectangular Point Reconstruction for Domain Adaptive Multimodal 3D Object Detection in Adverse Weather Conditions (AAAI 2025 · similarity 0.87)
- Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection (AAAI 2024 · similarity 0.87)
- Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather (CVPR 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.
