AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Score-Based Point Cloud Denoising

Shitong Luo, Wei Hu

ICCV 2021 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 227 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 score-based gradient ascent update instead of direct score addition (ablation)Score-based point cloud denoiser · PU test set, 10K points, 1% noiseChamfer distance: 3.237 -> 2.521Improved
add score-based gradient ascent update instead of direct score addition (ablation)Score-based point cloud denoiser · PU test set, 10K points, 3% noiseChamfer distance: 7.471 -> 4.708Improved
add iterative application to direct displacement update (ablation)Score-based point cloud denoiser · PU test set, 10K points, 3% noiseChamfer distance: 7.471 -> 6.073Improved
add iterative application to direct displacement update (ablation)Score-based point cloud denoiser · PU test set, 10K points, 1% and 2% noiseChamfer distance: 3.237 -> 3.237No clear effect
add neighborhood-covering training objective instead of point-position objective (ablation)Score-based point cloud denoiser · PU test set, 10K points, 1% noiseChamfer distance: 4.726 -> 2.521Improved
add neighborhood-covering training objective instead of point-position objective (ablation)Score-based point cloud denoiser · PU test set, 10K points, 3% noiseChamfer distance: 5.976 -> 4.708Improved
add ensemble score function instead of single score function (ablation)Score-based point cloud denoiser · PU test set, 10K points, 1% noiseChamfer distance: 2.522 -> 2.521Improved
add ensemble score function instead of single score function (ablation)Score-based point cloud denoiser · PU test set, 10K points, 3% noiseChamfer distance: 6.872 -> 4.708Improved
add ensemble score function instead of single score function (ablation)Score-based point cloud denoiser · PU test set, 10K points, 3% noisePoint-to-mesh distance: 3.497 -> 1.942Improved
use denoiser trained on Gaussian noise only on unseen simulated LiDAR noiseScore-based point cloud denoiser · Simulated LiDAR noise 1%Chamfer distance: 2.663 -> 2.616Improved
use denoising-based upsampling instead of specialized PU-NetScore-based point cloud denoiser · PU upsampling 4x, 5K inputChamfer distance: 3.445 -> 1.696Improved
use denoising-based upsampling instead of specialized PU-NetScore-based point cloud denoiser · PU upsampling 4x, 10K inputChamfer distance: 2.862 -> 1.454Improved

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