AI Paper Atlas

Research map / 3D vision / Face and shape

Analyzing Clothing Layer Deformation Statistics of 3D Human Motions

Jinlong Yang, Jean-Sebastien Franco, Franck Hetroy-Wheeler, Stefanie Wuhrer

ECCV 2018 · 3D vision › Face and shape · approach: Clothed human modeling · 68 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
keep 40 principal components instead of 5 for offset clothing layer reconstruction (ablation)PCA clothing layer model · PCA reconstruction, Bouncing sequencereconstruction error (mm): 22.52 -> 6.49Improved
keep 40 principal components instead of 5 (ablation)PCA clothing layer model · PCA reconstruction, Squat 1 sequencereconstruction error (mm): 18.94 -> 2.67Improved
keep 40 principal components instead of 1 (ablation)PCA clothing layer model · PCA reconstruction, Squat 1 sequencereconstruction error (mm): 46.33 -> 2.67Improved
keep all principal components instead of 40 (ablation)PCA clothing layer model · PCA reconstruction, Bouncing sequencereconstruction error (mm): 6.49 -> 0.10Improved
use more principal components (ablation)PCA clothing layer model · PCA reconstruction, 10 sequencesaverage reconstruction errorImproved
use fuzzy association with higher nf instead of nf = 1 (ablation)offset clothing layer extraction · skirt sequenceseam artifacts (qualitative)Improved
regress PCA coefficients from motion with a neural network, tested on held-out framesclothing regression · Crane sequenceprediction error (mm): 4.71 -> 4.28No clear effect
evaluate regression on held-out frames versus training framesclothing regression · Samba sequenceerror (mm): 4.27 -> 7.44Hurt
add Gaussian noise to material and size parameters during regression trainingmaterial and fit regression · material and clothing fit synthesisoverfitting to few training points (qualitative)Improved
reduce material parameters from 39 to 4 dimensions and deformation space with PCAmaterial regression · simulated garment, held-out materialwrinkle detail (qualitative)Hurt

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