AI Paper Atlas

Research map / Point clouds / Point cloud classification

Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds Using Convolutional Neural Networks

Yizhak Ben-Shabat, Michael Lindenbaum, Anath Fischer

CVPR 2019 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 120 citations (OpenAlex)

Check 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
learn a local scale choice with the mixture-of-experts scale manager rather than use a fixed single scale (ablation)Nesti-Net · PCPNet test set, averageRMS angle error: 23.91 -> 12.41Improved
select an expert scale rather than concatenate multiple scales (ablation)Nesti-Net · PCPNet test set, averageRMS angle error: 16.11 -> 12.41Improved
learn scale selection without noise-level labels rather than switch using a provided noise level (ablation)Nesti-Net · PCPNet test set, averageRMS angle error: 13.55 -> 12.41Improved
use three scales instead of two (ablation)Nesti-Net · PCPNet test set, averageRMS angle error: 12.97 -> 12.41Improved
use learned scale selection rather than noise-based switching (ablation)Nesti-Net · PCPNet test set, noise σ = 0.012RMS angle error: 22.59 -> 22.28Improved
use learned scale selection rather than noise-based switching (ablation)Nesti-Net · PCPNet test set, Gradient densityRMS angle error: 11.89 -> 9.00Improved
use Nesti-Net instead of the strongest reported baselinenormal estimation · PCPNet test set, Gradient densityRMS angle error: 8.49 -> 9.00Hurt
use Nesti-Net instead of PCPNet ssnormal estimation · PCPNet test set, averagePGP10: 0.7393 -> 0.8120Improved
use Nesti-Net instead of PCPNet ssnormal estimation · PCPNet test set, averagePGP5: 0.5526 -> 0.6617Improved

Later papers that compared with this method

6 later accepted papers report Nesti-Net as a baseline in their results tables; 6 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