AI Paper Atlas

Research map / Point clouds / Point cloud classification

Learning Graph-Convolutional Representations for Point Cloud Denoising

Francesca Pistilli, Giulia Fracastoro, Diego Valsesia, Enrico Magli

ECCV 2020 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 95 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
use dynamic feature-space graph instead of fixed 3D graph (ablation)GPDNet MSE · ShapeNet sigma=0.015, 8-NNChamfer: 37.00 -> 35.68Improved
use dynamic feature-space graph instead of fixed 3D graph (ablation)GPDNet MSE-SP · ShapeNet sigma=0.015, 8-NNChamfer: 38.45 -> 36.99Improved
use dynamic feature-space graph instead of fixed 3D graph (ablation)GPDNet MSE · ShapeNet sigma=0.015, 8-NNUNAE: 23.75 -> 23.56Improved
use dynamic feature-space graph instead of fixed 3D graph (ablation)GPDNet MSE-SP · ShapeNet sigma=0.015, 8-NNUNAE: 26.65 -> 26.29Improved
increase neighbors from 4 to 16 (ablation)GPDNet MSE-SP · ShapeNet sigma=0.02Chamfer: 64.63 -> 49.26Improved
increase neighbors from 16 to 24 (ablation)GPDNet MSE-SP · ShapeNet sigma=0.02Chamfer: 49.26 -> 50.43Hurt
increase neighbors from 16 to 24 (ablation)GPDNet MSE · ShapeNet sigma=0.02Chamfer: 52.96 -> 55.45Hurt
increase neighbors from 4 to 16 (ablation)GPDNet MSE · ShapeNet sigma=0.01UNAE: 27.22 -> 20.11Improved
add proximity-to-surface term to MSE loss (MSE-SP) (ablation)GPDNet · ShapeNet airplane sigma=0.02Chamfer: 45.96 -> 42.30Improved
add proximity-to-surface term to MSE loss (MSE-SP) (ablation)GPDNet · ShapeNet airplane sigma=0.01Chamfer: 17.22 -> 17.58Hurt
add proximity-to-surface term to MSE loss (MSE-SP) (ablation)GPDNet · Normal estimation sigma=0.02UNAE: 22.78 -> 27.06Hurt
add proximity-to-surface term to MSE loss (MSE-SP) (ablation)GPDNet · Simulated Velodyne structured noiseRMSD: 0.0664 -> 0.0602Improved

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