AI Paper Atlas

Research map / Point clouds / Point cloud classification

Clustering based Point Cloud Representation Learning for 3D Analysis

Tuo Feng, Wenguan Wang, Xiaohan Wang, Yi Yang, Qinghua Zheng

ICCV 2023 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 47 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 point-point contrast (ablation)KPConv · S3DIS Area-5mIoU: 67.1 -> 68.0Improved
add point-center contrast (ablation)KPConv · S3DIS Area-5mIoU: 67.1 -> 68.4Improved
combine point-point and point-center contrast (ablation)KPConv · S3DIS Area-5mIoU: 67.1 -> 69.0Improved
combine point-point and point-center contrast (ablation)KPConv · SemanticKITTI multi-scan valmIoU: 53.3 -> 55.7Improved
add point-point contrast (ablation)KPConv · SemanticKITTI multi-scan valmIoU: 53.3 -> 54.4Improved
add point-center contrast (ablation)KPConv · SemanticKITTI multi-scan valmIoU: 53.3 -> 54.7Improved
add clustering-based training (training cost) (ablation)KPConv · S3DIS Area-5training time per epoch: 281.46 -> 311.71Hurt
split each class into M=40 sub-clusters instead of M=1 (ablation)KPConv · S3DIS Area-5mIoU: 67.5 -> 69.0Improved
split each class into M=40 sub-clusters instead of M=1 (ablation)KPConv · SemanticKITTI multi-scan valmIoU: 53.7 -> 55.7Improved
increase cluster number M above 40 (ablation)KPConv · S3DIS Area-5mIoUNo clear effect
add class-wise memory bank (10 points per scene per cluster) over mini-batch-only contrast (ablation)KPConv · S3DIS Area-5mIoU: 68.0 -> 69.0Improved
add class-wise memory bank (10 points per scene per cluster) over mini-batch-only contrast (ablation)KPConv · SemanticKITTI multi-scan valmIoU: 54.4 -> 55.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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