AI Paper Atlas

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

ICCV 2025 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
add current occupancy reconstruction L_recon (ablation)TOP · nuScenes MOS (5% labels)Recall_obj: 24.56 -> 25.75Improved
add current occupancy reconstruction L_recon (ablation)TOP · nuScenes MOS (5% labels)IoU_w/o: 35.35 -> 35.94Improved
pre-train with TOP versus training from scratchsparse 4D UNet · nuScenes MOS (10% labels)Recall_obj: 24.98 -> 28.03Improved
pre-train with TOP versus training from scratchsparse 4D UNet · SemanticKITTI MOS (20% labels)Recall_obj: 47.41 -> 58.45Improved
pre-train with ALSO versus scratchsparse 4D UNet · SemanticKITTI MOS (10% labels)Recall_obj: 37.22 -> 9.21Hurt
pre-train with 4DOcc versus scratchsparse 4D UNet · SemanticKITTI MOS (10% labels)Recall_obj: 37.22 -> 8.54Hurt
pre-train with 4DOcc versus scratchsparse 4D UNet · nuScenes MOS (50% labels)IoU_w/o: 49.29 -> 46.73Hurt
pre-train with ALSO versus scratchsparse 4D UNet · nuScenes MOS (5% labels)Recall_obj: 24.27 -> 18.68Hurt
pre-train with UnO versus scratchsparse 4D UNet · nuScenes MOS (20% labels)Recall_obj: 25.59 -> 28.14Improved
pre-train with TOP versus scratchsparse 4D UNet · nuScenes MOS (20% labels)IoU_w/o: 44.25 -> 44.30No clear effect
pre-train with TOP versus scratchsparse 4D UNet · nuScenes semantic segmentation (10%)mIoU: 50.55 -> 50.97Improved
pre-train with 4DOcc versus scratchsparse 4D UNet · nuScenes semantic segmentation (10%)mIoU: 50.55 -> 47.49Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy