AI Paper Atlas

Research map / Point clouds / Shape and surface completion

GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping

Erhan Gundogdu, Victor Constantin, Amrollah Seifoddini, Minh Dang, Mathieu Salzmann, Pascal Fua

ICCV 2019 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 159 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 patch-wise garment features (Local or Global instead of late fusion) (ablation)GarNet · T-shirt draping (own dataset)E_dist (cm): 1.78 -> 0.93Improved
add patch-wise garment features (Local instead of late fusion) (ablation)GarNet · Jeans draping (own dataset)E_dist (cm): 2.13 -> 0.88Improved
add patch-wise garment features (Local instead of late fusion) (ablation)GarNet · Sweater draping (own dataset)E_dist (cm): 1.13 -> 0.97Improved
use nearest-neighbor pooled local body features (Local instead of Global) (ablation)GarNet · Jeans draping (own dataset)E_dist (cm): 1.01 -> 0.88Improved
use nearest-neighbor pooled local body features (Local instead of Global) (ablation)GarNet · T-shirt draping (own dataset)E_dist (cm): 1.05 -> 0.93Improved
use nearest-neighbor pooled local body features (Local instead of Global) (ablation)GarNet · Wang18 shirt datasetnormalized L2 distance (%): 1.15 -> 0.89Improved
GarNet-Local versus DQS skinning onlyT-shirt draping · T-shirt draping (own dataset)E_dist (cm): 9.98 -> 0.93Improved
GarNet-Local versus prior learned method Wang18shirt draping · Wang18 shirt datasetnormalized L2 distance (%): 3.01 -> 0.89Improved
GarNet-Local versus physics-based simulation in speedgarment draping · Garment draping (own dataset)computation time (ms): > 19000 -> 68Improved
reduce training poses from 50% to 25% of poses (ablation)GarNet-Local · T-shirt unseen posesE_dist (cm): 1.16 -> 1.68Hurt
add normal loss term and bending term to vertex+penetration loss (ablation)GarNet loss · Wang18 shirt dataset (loss ablation)E_normal (deg): 8.88 -> 7.36Improved
add bending term to vertex+penetration+normal loss (ablation)GarNet loss · Wang18 shirt dataset (loss ablation)E_dist: 1.08 -> 0.72Improved

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