AI Paper Atlas

Research map / Point clouds / Point cloud classification

PointNorm-Net: Self-Supervised Normal Prediction of 3D Point Clouds via Multi-Modal Distribution Estimation

Jie Zhang, Minghui Nie, Changqing Zou, Jian Liu, Ligang Liu, Junjie Cao

TPAMI 2025 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 2 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 candidate normal initialization (CNI), multi-candidate normals (ablation)PointNorm-Net · PCPNet synthetic datasetRMS angle error: 17.00 -> 16.46Improved
add adaptive neighborhood size (ANS) (ablation)PointNorm-Net · PCPNet synthetic datasetRMS angle error: 16.46 -> 14.79Improved
add feasible candidate filtering (FCF) (ablation)PointNorm-Net · PCPNet synthetic datasetRMS angle error: 14.79 -> 14.28Improved
add candidate consensus loss L_ccn (ablation)PointNorm-Net · PCPNet synthetic datasetRMS angle error: 13.73 -> 13.57Improved
add feature-preserving loss L_w (ablation)PointNorm-Net · PCPNet synthetic datasetRMS angle error: 13.97 -> 13.57Improved
reject 10% of initial candidates instead of none (ablation)PointNorm-Net · PCPNet synthetic datasetRMS angle error: 14.03 -> 13.57Improved
raise rejection ratio from 10% to 50% (ablation)PointNorm-Net · PCPNet synthetic datasetRMS angle error: 13.57 -> 13.61No clear effect
use 4 neighborhood segments instead of 2 (ablation)PointNorm-Net · PCPNet synthetic datasetRMS angle error: 13.81 -> 13.57No clear effect
replace direct optimization with a DeepFit-style network plus auxiliary lossesPointNorm-Opt · PCPNet synthetic datasetRMS angle error: 14.86 -> 13.57Improved
use AdaFit predictor instead of DeepFit predictorPointNorm-Net · PCPNet synthetic datasetRMS angle error: 13.57 -> 12.36Improved
use multi-scale instead of single-scale PCPNet predictorPointNorm-PCPNet · PCPNet synthetic datasetRMS angle error: 14.82 -> 14.36Improved
use point weight learning (DeepFit) instead of point normal learning (multi-scale PCPNet)PointNorm-Multi-PCPNet · PCPNet synthetic datasetRMS angle error: 14.36 -> 13.57Improved

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