AI Paper Atlas

Research map / Point clouds / Shape and surface completion

SIMPC: Learning Self-Induced Mirror-Point Consistency for Unsupervised Point Cloud Denoising

Chengwei Zhang, Xueyi Zhang, Tao Jiang, Xinhao Xu, Wenjie Li, Fubo Zhang, Longyong Chen

ICML 2026 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 0 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 mirror-point consistency loss on top of CD similarity loss (ablation)SIMPC · PUNet 10K 3% GaussianChamfer distance: 65.73 -> 34.42Improved
add mirror-point consistency loss on top of CD similarity loss (ablation)SIMPC · PUNet 10K 3% GaussianP2M distance: 36.20 -> 13.85Improved
use mirror-point consistency instead of EMD similarity (ablation)SIMPC · PUNet 10K 3% GaussianChamfer distance: 41.04 -> 34.42Improved
use EMD similarity instead of CD only (ablation)SIMPC · PUNet 10K 3% GaussianChamfer distance: 65.73 -> 41.04Improved
use EMD instead of CD-only similarity loss (ablation)SIMPC · PUNet 10K 1% GaussianChamfer distance: 18.91 -> 26.54Hurt
use symmetric extension w2 = 2 instead of 1.5 (ablation)SIMPC mirror-point generation · PUNet 10K 3% GaussianChamfer distance: 35.10 -> 34.42Improved
use symmetric extension w2 = 2 instead of 2.5 (ablation)SIMPC mirror-point generation · PUNet 10K 3% GaussianChamfer distance: 36.33 -> 34.42Improved
SIMPC vs best prior unsupervised method U-CANSIMPC · PUNet 10K 1% GaussianChamfer distance: 24.97 -> 20.25Improved
SIMPC vs Noise2Score3D on non-Gaussian noiseSIMPC · PUNet 10K 1% LaplacianChamfer distance: 43.08 -> 23.65Improved
SIMPC vs Score-U on real scansSIMPC · KinectChamfer distance: 15.85 -> 13.01Improved
SIMPC vs supervised PD-RefinerSIMPC · PUNet 10K 1% GaussianChamfer distance: 17.54 vs 20.25Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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