Research map / Point clouds / Segmentation and detection
Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation
Aoran Xiao, Jiaxing Huang, Dayan Guan, Fangneng Zhan, Shijian Lu
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 PCT-translated SynLiDAR to SemanticKITTI training | Data augmentation with MinkowskiNet · SemanticKITTI val | mIoU: 62.5 -> 64.7 | Improved |
| Add PCT-translated SynLiDAR to SemanticPOSS training | Data augmentation with MinkowskiNet · SemanticPOSS val | mIoU: 53.2 -> 55.8 | Improved |
| Add PCT-translated SynLiDAR to S+T training | SSDA with MinkowskiNet · SemanticKITTI val | mIoU: 22.6 -> 24.8 | Improved |
| Add PCT-translated SynLiDAR to S+T training | SSDA with MinkowskiNet · SemanticPOSS val | mIoU: 24.3 -> 28.8 | Improved |
| Add PCT to APE | SSDA with MinkowskiNet · SemanticKITTI val | mIoU: 25.1 -> 27.0 | Improved |
| Add PCT to APE | SSDA with MinkowskiNet · SemanticPOSS val | mIoU: 30.3 -> 31.2 | Improved |
| Add PCT-translated SynLiDAR to source-only training | UDA with MinkowskiNet · SemanticKITTI val | mIoU: 20.4 -> 23.9 | Improved |
| Add PCT-translated SynLiDAR to source-only training | UDA with MinkowskiNet · SemanticPOSS val | mIoU: 20.1 -> 22.9 | Improved |
| Add PCT to ST | UDA with MinkowskiNet · SemanticKITTI val | mIoU: 26.5 -> 28.9 | Improved |
| Add PCT to ST | UDA with MinkowskiNet · SemanticPOSS val | mIoU: 27.1 -> 29.6 | Improved |
Closest papers by meaning
- Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation (TPAMI 2023 · similarity 0.89)
- ProtoTransfer: Cross-Modal Prototype Transfer for Point Cloud Segmentation (ICCV 2023 · similarity 0.89)
- Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion (CVPR 2021 · similarity 0.88)
- Less Is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation (CVPR 2023 · similarity 0.88)
- Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation (NeurIPS 2023 · similarity 0.88)
- LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes (CVPR 2024 · similarity 0.88)
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.
