Research map / Point clouds / Segmentation and detection
Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather
Junsung Park, Kyungmin Kim, Hyunjung Shim
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 Angle-Selective Jittering to training (ablation) | MinkowskiNet · SemanticKITTI to SemanticSTF | mIoU: 31.4 -> 36.8 | Improved |
| add Depth-Selective Jittering (ablation) | MinkowskiNet · SemanticKITTI to SemanticSTF | mIoU: 31.4 -> 37.6 | Improved |
| add Range Jittering (ablation) | MinkowskiNet · SemanticKITTI to SemanticSTF | mIoU: 31.4 -> 38.7 | Improved |
| add Learnable Point Drop (DQN-based) on top of jittering (ablation) | MinkowskiNet · SemanticKITTI to SemanticSTF | mIoU: 31.4 -> 39.5 | Improved |
| add LPD vs Range Jittering in snow (ablation) | MinkowskiNet · SemanticSTF Snow | mIoU: 33.5 -> 33.1 | Hurt |
| apply augmentation to clean data performance (ablation) | MinkowskiNet · SemanticKITTI clean val | mIoU: 63.9 -> 62.8 | Hurt |
| apply the proposed augmentations to SPVCNN on SemanticKITTI-C | SPVCNN · SemanticKITTI-C | mIoU: 52.5 -> 52.9 | No clear effect |
| apply the proposed augmentations to CENet | CENet · SemanticSTF | mIoU: 14.2 -> 22.0 | Improved |
| apply the proposed augmentations to SPVCNN | SPVCNN · SemanticSTF | mIoU: 28.1 -> 38.4 | Improved |
| increase random point drop from soft to hard | MinkowskiNet (toy experiment) · SemanticKITTI val | mIoU: 61.8 -> 27.7 | Hurt |
| increase intensity distortion from soft to hard | MinkowskiNet (toy experiment) · SemanticKITTI val | mIoU: 62.3 -> 56.8 | Hurt |
Closest papers by meaning
- No Thing, Nothing: Highlighting Safety-Critical Classes for Robust LiDAR Semantic Segmentation in Adverse Weather (CVPR 2025 · similarity 0.93)
- Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather (CVPR 2025 · similarity 0.92)
- UniMix: Towards Domain Adaptive and Generalizable LiDAR Semantic Segmentation in Adverse Weather (CVPR 2024 · similarity 0.91)
- Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention (AAAI 2024 · similarity 0.89)
- Parsing All Adverse Scenes: Severity-Aware Semantic Segmentation with Mask-Enhanced Cross-Domain Consistency (AAAI 2024 · similarity 0.87)
- Semantic Segmentation on Raindrop Degraded Images Using Two-Stage Dual Teacher-Student Learning (AAAI 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.
