AI Paper Atlas

Research map / 3D vision / Face and shape

DrapeNet: Garment Generation and Self-Supervised Draping

Luca De Luigi, Ren Li, Benoît Guillard, Mathieu Salzmann, Pascal Fua

CVPR 2023 · 3D vision › Face and shape · approach: Clothed human modeling · 49 citations (OpenAlex)

Read the paper

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 self-supervised physics-based draping with a garment-conditioned refinement fieldDrapeNet · CLOTH3D test top garmentsB2G-top (%): 7.2 -> 0.9Improved
Use self-supervised physics-based draping with a garment-conditioned refinement fieldDrapeNet · CLOTH3D test bottom garmentsB2G-bottom (%): 3.4 -> 0.3Improved
Use the Intersection Solver (ablation)DrapeNet · CLOTH3D test top-bottom garment pairsG2G (%): 1.1 -> 0.5Improved
Use physics-based self-supervision rather than matching the simulator's exact vertex locationsDrapeNet · CLOTH3D test top garmentsED-top (mm): 28.1 -> 47.9Hurt
Use physics-based self-supervision rather than matching the simulator's exact vertex locationsDrapeNet · CLOTH3D test bottom garmentsED-bottom (mm): 18.3 -> 27.3Hurt
Add gradient supervision to the garment UDF training loss (ablation)DrapeNet garment generative network · Garment reconstruction test examplessurface qualityImproved
Use BCE instead of L1 for the distance loss, with gradient supervision (ablation)DrapeNet garment generative network · Garment reconstruction test examplessurface qualityImproved
Use BCE instead of L2 for the distance loss, with gradient supervision (ablation)DrapeNet garment generative network · Garment reconstruction test examplesholes in reconstructed surfacesImproved
Add a waist-and-hip pin loss for bottom garments (ablation)DrapeNet bottom draping network · Bottom garment drapingdeformation naturalnessImproved
Set the pin-loss λ to 0 or 1 instead of 0.1 (ablation)DrapeNet bottom draping network · Bottom garment drapingdeformation naturalnessHurt
Add the layer loss to enforce top-bottom garment ordering (ablation)DrapeNet · Top-bottom garment drapinggarment intersectionsImproved
Condition the refinement field on the correct garment latent code (ablation)DrapeNet · Garment draping with mismatched latent codesdeformation realismImproved

Later papers that compared with this method

5 later accepted papers report DrapeNet as a baseline in their results tables; 5 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