Research map / Label-efficient and robust learning / Domain adaptation and generalization
CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection
Read the paperCheck 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 |
|---|---|---|---|
| Use CL3D instead of ST3D | CenterPoint adaptation · nuScenes → PandaSet | mAP: 0.617 -> 0.705 | Helped |
| Use CL3D instead of ST3D | CenterPoint adaptation · PandaSet → nuScenes | mAP: 0.349 -> 0.467 | Helped |
| Use CL3D instead of ST3D | CenterPoint adaptation · Waymo → PandaSet | mAP: 0.704 -> 0.729 | Helped |
| Use CL3D instead of ST3D | CenterPoint adaptation · PandaSet → Waymo | mAP: 0.423 -> 0.492 | Helped |
| Use CL3D instead of ST3D | CenterPoint adaptation · nuScenes → KITTI | mAP: 0.625 -> 0.682 | Helped |
| Use CL3D instead of ST3D | CenterPoint adaptation · KITTI → nuScenes | mAP: 0.289 -> 0.305 | Helped |
| Use CL3D rather than SRDAN | PreSIL → KITTI adaptation · KITTI Easy | mAP(Car): 25.9 -> 28.0 | Helped |
| Use CL3D rather than SRDAN | PreSIL → KITTI adaptation · KITTI Mod. | mAP(Car): 22.1 -> 25.3 | Helped |
| Use CL3D rather than SRDAN | PreSIL → KITTI adaptation · KITTI Hard | mAP(Car): 18.7 -> 23.4 | Helped |
| Add spatial geometry alignment and temporal motion alignment (ablation) | CL3D · nuScenes → PandaSet | mAP: 0.641 -> 0.705 | Helped |
| Add temporal motion alignment (ablation) | CL3D with SGA · nuScenes → PandaSet | mAP: 0.686 -> 0.705 | Helped |
| Add spatial geometry alignment (ablation) | CL3D with TMA · nuScenes → PandaSet | mAP: 0.662 -> 0.705 | Helped |
Closest papers by meaning
- CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection (AAAI 2024 · similarity 0.90)
- D^3CTTA: Domain-Dependent Decorrelation for Continual Test-Time Adaption of 3D LiDAR Segmentation (CVPR 2025 · similarity 0.88)
- An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains (CVPR 2024 · similarity 0.88)
- MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection (ICLR 2025 · similarity 0.88)
- GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection (CVPR 2025 · similarity 0.87)
- LiT: Unifying LiDAR "Languages" with LiDAR Translator (NeurIPS 2024 · 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.