AI Paper Atlas

Research map / 3D vision / Face and shape

SNUG: Self-Supervised Neural Dynamic Garments

Igor Santesteban, Miguel A. Otaduy, Dan Casas

CVPR 2022 · 3D vision › Face and shape · approach: Clothed human modeling · 114 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
Use SNUG's physics-based self-supervised training instead of PBNSGarment deformation model · AMASS test setstrain loss: 0.111 -> 0.064Improved
Use SNUG's physics-based self-supervised training instead of PBNSGarment deformation model · AMASS test setbending loss: 0.007 -> 0.004Improved
Use SNUG's physics-based self-supervised training instead of PBNSGarment deformation model · AMASS test setgravity loss: 0.044 -> 0.028Improved
Use SNUG's physics-based self-supervised training instead of PBNSGarment deformation model · AMASS test setinertia loss: 0.0035 -> 0.0034Improved
Add bending loss (ablation)SNUG · Ground-truth simulated test setmean-curvature error: 17.3 -> 2.7Improved
Add strain loss (ablation)SNUG · Ground-truth simulated test setmean-curvature error: 19.1 -> 2.7Improved
Add gravity loss (ablation)SNUG · Ground-truth simulated test setmean-curvature error: 7.5 -> 2.7Improved
Add inertia loss (ablation)SNUG · Ground-truth simulated test setmean-curvature error: 2.8 -> 2.7Improved
Initialize GRU hidden states with sampled noise rather than zerosSNUG recurrent regressor · Long motion sequencesgeneralization to longer sequencesImproved
Train on 3-frame subsequences rather than longer subsequencesSNUG recurrent regressor · Dynamic garment deformationdynamic deformation qualityImproved

Later papers that compared with this method

1 later accepted paper reports SNUG as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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