Research map / Point clouds / Segmentation and detection
Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation
Ziliang Miao, Runjian Chen, Yixi Cai, Buwei He, Wenquan Zhao, Wenqi Shao, Bo Zhang, Fu Zhang
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 current occupancy reconstruction L_recon (ablation) | TOP · nuScenes MOS (5% labels) | Recall_obj: 24.56 -> 25.75 | Improved |
| add current occupancy reconstruction L_recon (ablation) | TOP · nuScenes MOS (5% labels) | IoU_w/o: 35.35 -> 35.94 | Improved |
| pre-train with TOP versus training from scratch | sparse 4D UNet · nuScenes MOS (10% labels) | Recall_obj: 24.98 -> 28.03 | Improved |
| pre-train with TOP versus training from scratch | sparse 4D UNet · SemanticKITTI MOS (20% labels) | Recall_obj: 47.41 -> 58.45 | Improved |
| pre-train with ALSO versus scratch | sparse 4D UNet · SemanticKITTI MOS (10% labels) | Recall_obj: 37.22 -> 9.21 | Hurt |
| pre-train with 4DOcc versus scratch | sparse 4D UNet · SemanticKITTI MOS (10% labels) | Recall_obj: 37.22 -> 8.54 | Hurt |
| pre-train with 4DOcc versus scratch | sparse 4D UNet · nuScenes MOS (50% labels) | IoU_w/o: 49.29 -> 46.73 | Hurt |
| pre-train with ALSO versus scratch | sparse 4D UNet · nuScenes MOS (5% labels) | Recall_obj: 24.27 -> 18.68 | Hurt |
| pre-train with UnO versus scratch | sparse 4D UNet · nuScenes MOS (20% labels) | Recall_obj: 25.59 -> 28.14 | Improved |
| pre-train with TOP versus scratch | sparse 4D UNet · nuScenes MOS (20% labels) | IoU_w/o: 44.25 -> 44.30 | No clear effect |
| pre-train with TOP versus scratch | sparse 4D UNet · nuScenes semantic segmentation (10%) | mIoU: 50.55 -> 50.97 | Improved |
| pre-train with 4DOcc versus scratch | sparse 4D UNet · nuScenes semantic segmentation (10%) | mIoU: 50.55 -> 47.49 | Hurt |
Closest papers by meaning
- Temporal Consistent 3D LiDAR Representation Learning for Semantic Perception in Autonomous Driving (CVPR 2023 · similarity 0.89)
- MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory (ICCV 2023 · similarity 0.89)
- Spatiotemporal Self-Supervised Learning for Point Clouds in the Wild (CVPR 2023 · similarity 0.89)
- HiLoTs: High-Low Temporal Sensitive Representation Learning for Semi-Supervised LiDAR Segmentation in Autonomous Driving (CVPR 2025 · similarity 0.88)
- TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception (NeurIPS 2025 · similarity 0.88)
- Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations (CVPR 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.
