Research map / Point clouds / Segmentation and detection
Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| complete source and target LiDAR surfaces before segmentation | MinkowskiNet semantic segmentation · Waymo→nuScenes-lidarseg, nuScenes-lidarseg→Waymo, SemanticKITTI→Waymo, nuScenes-lidarseg→SemanticKITTI, SemanticKITTI→nuScenes-lidarseg, Waymo→SemanticKITTI | mIoU (%): 42.9 -> 50.2; 46.2 -> 59.7; 46.3 -> 52.0; 23.5 -> 33.7; 27.9 -> 31.6; 55.0 -> 60.4 | Helped |
| add the structure refinement network (ablation) | Complete & Label · Waymo→nuScenes-lidarseg | mIoU (%): 46.6 -> 50.2 | Helped |
| add the structure refinement network (ablation) | Complete & Label · nuScenes-lidarseg→Waymo | mIoU (%): 58.2 -> 59.8 | Helped |
| add the structure refinement network (ablation) | Complete & Label · nuScenes-lidarseg→SemanticKITTI | mIoU (%): 30.1 -> 33.7 | Helped |
| add the structure refinement network (ablation) | Complete & Label · SemanticKITTI→nuScenes-lidarseg | mIoU (%): 29.6 -> 31.6 | Helped |
| add the structure refinement network (ablation) | Complete & Label · Waymo→SemanticKITTI | mIoU (%): 58.8 -> 60.4 | Helped |
| add the structure refinement network (ablation) | Complete & Label · SemanticKITTI→Waymo | mIoU (%): 50.3 -> 52.0 | Helped |
| add local adversarial loss (ablation) | Complete & Label · Waymo→nuScenes-lidarseg | mIoU (%): 49.1 -> 50.2 | Helped |
| add local adversarial loss (ablation) | Complete & Label · nuScenes-lidarseg→Waymo | mIoU (%): 59.0 -> 59.8 | Helped |
| add local adversarial loss (ablation) | Complete & Label · nuScenes-lidarseg→SemanticKITTI | mIoU (%): 32.4 -> 33.7 | Helped |
| add local adversarial loss (ablation) | Complete & Label · SemanticKITTI→nuScenes-lidarseg | mIoU (%): 30.7 -> 31.6 | Helped |
| add local adversarial loss (ablation) | Complete & Label · Waymo→SemanticKITTI | mIoU (%): 59.5 -> 60.4 | Helped |
Closest papers by meaning
- Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation (NeurIPS 2023 · similarity 0.90)
- Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation (CVPR 2022 · similarity 0.90)
- Construct to Associate: Cooperative Context Learning for Domain Adaptive Point Cloud Segmentation (CVPR 2024 · similarity 0.90)
- Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation (CVPR 2025 · similarity 0.88)
- Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models (NeurIPS 2024 · similarity 0.88)
- TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception (NeurIPS 2025 · 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.