AI Paper Atlas

Research map / Point clouds / Point cloud classification

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Youquan Liu, Lingdong Kong, Jun CEN, Runnan Chen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu

NeurIPS 2023 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 29 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
use VFM (SEEM) semantic superpixels instead of SLIC (ablation)Seal · nuScenes linear probingmIoU: 40.89 -> 44.95Improved
use VFM superpixels (SEEM) in SLidR (ablation)SLidR · nuScenes linear probingmIoU: 38.80 -> 43.00Improved
add VFM superpixels to camera-to-LiDAR distillation (ablation)Seal · nuScenes linear probingmIoU: 38.80 -> 43.00Improved
add superpoint temporal consistency to C2L distillation (ablation)Seal · nuScenes linear probingmIoU: 38.80 -> 40.45Improved
add temporal consistency on top of VFM (ablation)Seal · nuScenes linear probingmIoU: 43.00 -> 44.01Improved
add point-to-segment regularization on top of VFM (ablation)Seal · nuScenes linear probingmIoU: 43.00 -> 43.35Improved
add point-to-segment regularization to VFM+STC (full model) (ablation)Seal · nuScenes linear probingmIoU: 44.01 -> 44.95Improved
add temporal consistency or P2S when fully fine-tuning on nuScenes (ablation)Seal · nuScenes full fine-tunemIoU: 75.21 -> 75.60No clear effect
add temporal consistency to VFM at 5% nuScenes fine-tune (ablation)Seal · nuScenes 5% fine-tunemIoU: 53.03 -> 55.36Improved
use SAM instead of SEEM superpixels (ablation)Seal · nuScenes full fine-tunemIoU: 75.60 -> 75.92Improved
use SAM instead of SEEM superpixels (ablation)Seal · nuScenes linear probingmIoU: 44.95 -> 43.94Hurt
Seal pretraining instead of SLidR under 10% sensor misalignmentSLidR · nuScenes 1% fine-tunemIoU: 37.30 -> 44.80Improved

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