AI Paper Atlas

Research map / Point clouds / Point cloud classification

Constraint-Aware Feature Learning for Parametric Point Cloud

Xi Cheng, Ruiqi Lei, Di Huang, Zhichao Liao, Fengyuan Piao, Yan Chen, Pingfa Feng, Long Zeng

ICCV 2025 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 4 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 MAD component (ablation)CstNet · Param20Kinstance accuracy: 86.32 -> 89.94Improved
add Adjacency component (ablation)CstNet · Param20Kinstance accuracy: 88.14 -> 89.94Improved
add Primitive Type component (ablation)CstNet · Param20Kinstance accuracy: 88.68 -> 89.94Improved
add all three constraint components (ablation)CstNet · Param20Kinstance accuracy: 83.99 -> 89.94Improved
use SurfaceKNN instead of KNN (ablation)CstNet · Param20Kinstance accuracy: 89.03 -> 89.94Improved
use SurfaceKNN when Primitive Type disabled (ablation)CstNet · Param20Kinstance accuracy: 88.73 -> 88.68No clear effect
use predicted instead of label constraintsCstNet · Param20Kinstance accuracy: 91.80 -> 89.94Hurt
use Stage 2 backbone of CstNet vs DGCNN with predicted constraints (ablation)CstNet · Param20Kinstance accuracy: 86.81 -> 89.94Improved
add constraint-aware features to PointNet++ for prism-cuboid classification (ablation)PointNet++ · Prism-Cuboid 50 to 87 degreesaccuracyImproved
add constraints on 89 degree prismsCstNet · Prism-Cuboid 89 degreesaccuracyNo clear effect
CstPnt vs ParSeNet on unseen Param20K Primitive Type predictionCstPnt · Param20K (unseen)primitive type accuracy: 59.75 -> 86.52Improved
CstNet vs PTMamba classificationCstNet · Param20Kinstance accuracy: 86.45 -> 89.94Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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