AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Denoise and Contrast for Category Agnostic Shape Completion

Antonio Alliegro, Diego Valsesia, Giulia Fracastoro, Enrico Magli, Tatiana Tommasi

CVPR 2021 · Point clouds › Shape and surface completion · approach: Point cloud completion networks · 34 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
add denoising pretraining (ablation)DeCo · Known categoriesChamfer Distance ×10^4: 23.865 -> 21.022Improved
add contrastive pretraining (ablation)DeCo · Known categoriesChamfer Distance ×10^4: 23.865 -> 23.067Improved
combine denoising and contrastive pretraining (ablation)DeCo · Known categoriesChamfer Distance ×10^4: 21.022 -> 18.742Improved
add frame reconstruction constraint (ablation)DeCo with denoising and contrastive pretraining · Known categoriesChamfer Distance ×10^4: 18.742 -> 16.517Improved
replace contrastive pretraining with supervised classification (ablation)DeCo · Known categoriesChamfer Distance ×10^4: 16.517 -> 18.699Hurt
replace the GPDNet denoising encoder with DGCNN (ablation)DeCo · Known categoriesChamfer Distance ×10^4: 16.517 -> 19.667Hurt
use contrastive pairs instead of quadruplets (ablation)DeCo global encoder · Known categoriesChamfer Distance ×10^4: 16.517 -> 18.030Hurt
vary the auxiliary frame size and decoder node count (ablation)DeCo · Known categoriesChamfer Distance ×10^4: 16.517; 17.693; 18.068; 18.129; 18.595; 19.001Mixed
train without denoising, contrastive pretraining, or frame constraint (ablation)DeCo · Novel categories, similarChamfer Distance ×10^4: 19.364 -> 26.811Hurt
train without denoising, contrastive pretraining, or frame constraint (ablation)DeCo · Novel categories, dissimilarChamfer Distance ×10^4: 32.945 -> 40.419Hurt
add denoising and contrastive pretraining (ablation)DeCo · Novel categories, similarChamfer Distance ×10^4: 26.811 -> 19.364Improved
add denoising and contrastive pretraining (ablation)DeCo · Novel categories, dissimilarChamfer Distance ×10^4: 40.419 -> 32.945Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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