AI Paper Atlas

Research map / Point clouds / Segmentation and detection

PointDC: Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-Modal Distillation and Super-Voxel Clustering

Zisheng Chen, Hongbin Xu, Weitao Chen, Zhipeng Zhou, Haihong Xiao, Baigui Sun, Xuansong Xie, Wenxiong kang

ICCV 2023 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 32 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 multi-view 2D clustering over random 3D clustering (ablation)random clustering · ScanNet-v2 valmIoU: 3.86 -> 13.58Improved
add cross-modal distillation (CMD) (ablation)PointDC · ScanNet-v2 valmIoU: 13.58 -> 20.29Improved
add basic super-voxel clustering (ablation)PointDC · ScanNet-v2 valmIoU: 20.29 -> 23.64Improved
add non-parametric classifier (ablation)PointDC · ScanNet-v2 valmIoU: 23.64 -> 24.85Improved
add super-voxel pooling of pseudo labels (ablation)PointDC · ScanNet-v2 valmIoU: 24.85 -> 25.74Improved
add super-voxel pooling of pseudo labels (ablation)PointDC · ScanNet-v2 valaccuracy: 61.79 -> 63.69Improved
add super-voxel clustering stage after CMD with DGCNN (ablation)PointDC (DGCNN) · ScanNet-v2 valmIoU: 11.50 -> 14.06Improved
add super-voxel clustering stage after CMD with DGCNN (ablation)PointDC (DGCNN) · ScanNet-v2 valaccuracy: 39.65 -> 45.36Improved
PointDC versus best baseline STRL with DGCNN backboneDGCNN · ScanNet-v2 valunsupervised mIoU: +9.93 unsupervised mIoU and +24.84 unsupervised accuracyImproved
PointDC versus next best baseline on ScanNet-v2 testPointDC · ScanNet-v2 testmIoU: +18.4 unsupervised mIoUImproved

Later papers that compared with this method

3 later accepted papers report PointDC as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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