AI Paper Atlas

Research map / 3D vision / Face and shape

GarNet++: Improving Fast and Accurate Static 3D Cloth Draping by Curvature Loss

Erhan Gündoğdu, Victor Constantin, Shaifali Parashar, Amrollah Seifoddini, Minh Dang, Mathieu Salzmann, Pascal Fua

TPAMI 2020 · 3D vision › Face and shape · approach: Clothed human modeling · 59 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 mesh convolution patch-wise garment features (Late -> Global) (ablation)GarNet · Own dataset (SMPL), JeansE_dist (cm): 0.70 -> 0.42Improved
add explicit nearest-neighbour local body feature pooling (Global -> Local) (ablation)GarNet · Own dataset (SMPL), SweaterE_dist (cm): 0.93 -> 0.85Improved
use SMPL parameters as body input instead of point features (ablation)GarNet-Local · Own dataset (SMPL), JeansE_dist (cm): 0.41 -> 0.44No clear effect
add normal and bending terms to vert+pen loss (ablation)GarNet-Local · Wang datasetE_norm (deg): 10.01 -> 7.34Improved
add normal term to vert+pen+bend loss (ablation)GarNet-Local · Wang datasetE_norm (deg): 9.06 -> 7.34Improved
add bending term to vert+pen+norm loss (ablation)GarNet-Local · Wang datasetE_norm (deg): 7.91 -> 7.34Improved
add penetration term to vert+norm+bend loss (ablation)GarNet-Local · Wang datasetE_dist: 0.48 -> 0.42Improved
add RQ curvature loss to full loss (ablation)GarNet-Local · Wang datasetE_dist and E_norm: 0.42 -> 0.45 E_dist; 7.34 -> 7.2 E_normMixed
use RQ losses at multiple neighbourhood sizes (8+16+32) instead of 8-NN only (ablation)GarNet-Local-RQ · Own dataset (SMPL)E_norm (deg): 7.51 -> 7.2Improved
add RQ curvature fine-tuningGarNet-Local · Own dataset (SMPL), T-shirtE_norm (deg): 8.34 -> 7.79 E_norm; 0.56 -> 0.63 E_distMixed
use RQ loss instead of mean curvature normal loss (ablation)GarNet-Local · T-shirt (SMPL)E_norm (deg): 7.66 -> 7.79 E_norm; 0.26 -> 0.09 L_RQMixed
use RQ loss instead of uniform mean curvature loss (ablation)GarNet-Local · T-shirt (SMPL)E_norm (deg): 8.25 -> 7.79Improved

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