AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Self-supervised Garment Dynamics with Persistent Wrinkles

Xiaoyuan Yang, Deshan Gong, Taku Komura, He Wang

ECCV 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 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
use hinge-graph GNN message passing instead of RNN for P-Net (ablation)P-Net · Unseen motionsBED (rad): 0.86971 -> 0.28714Improved
use hinge-graph GNN message passing instead of LSTM for P-Net (ablation)P-Net · Unseen motionsBED (rad): 0.84272 -> 0.28714Improved
use hinge-graph GNN instead of Transformer for P-Net (ablation)P-Net · Unseen motionsBED (rad): 0.52095 -> 0.28714Improved
use hinge-graph GNN instead of Transformer for P-Net (ablation)P-Net · Unseen motionsFPS: 0.17 -> 9.43Improved
use hinge-graph GNN instead of Transformer for P-Net (ablation)P-Net · Unseen motionsGPU memory (GB): 9.2 -> 0.6Improved
use hinge-graph GNN instead of RNN for P-Net (ablation)P-Net · Unseen motionsBE (rad): 0.17048 -> 0.17118Hurt
increase message-passing steps from 1 to 3 (ablation)P-Net · P-Net RB predictionmean RB error (rad): 0.0281575 -> 0.017319Improved
increase message-passing steps from 2 to 3 (ablation)P-Net · P-Net RB predictionmax RB error (rad): 3.0522114 -> 2.975552Improved
increase alternating training cycles beyond four (ablation)EPNet training · Convergencetraining convergenceNo clear effect
add curriculum learning from elasticity to elasto-plasticity (ablation)EPNet training · Training stabilityconvergence stabilityImproved
model plasticity with learned rest bending versus best elastic baselineEPNet · Unseen motionsBED (rad): 45.34% in BED, 74.36% in PE, 2.79% in BE, 26.19% in MED, 32.50% in CD, 12.10% in BENImproved
model plasticity with learned rest bending versus best elastic baselineEPNet · Unseen bodiesBED (rad): 29.48% in BED, 32.78% in PE, 0.82% in BE, 13.38% in MED, 25.00% in CD, 18.93% in BENImproved

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