AI Paper Atlas

Research map / 3D vision / Face and shape

NeuralGarSim: Geometry-agnostic Garment Simulation with Neural Fields

Arihant Gaur, Navami Kairanda, Christian Theobalt, Vladislav Golyanik

ECCV 2026 · 3D vision › Face and shape · approach: Pixel-aligned implicit human and hand reconstruction · 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
formulate Kirchhoff-Love shell in 3D with tangential differential calculus instead of 2D parametric domainNeuralGarSim vs NeuralClothSim · Training time over 6 scenariostraining time: average 1h 6m 10s -> 31m 35sImproved
use TDC formulation instead of NeuralClothSimNeuralGarSim · Belytschko benchmarksmax displacement vs analytical: Scordelis-Lo 0.2965 -> 0.2987 (analytical 0.3024)No clear effect
represent deformation as continuous neural field rather than mesh-based simulatorNeuralGarSim vs DiffCloth · T-shirt under 3 discretisationswrinkle Chamfer distance dW: 0.035 -> 0.011 (M1,M2); 0.034 -> 0.013 (M1,M3)Improved
represent deformation as continuous neural field rather than mesh-based simulatorNeuralGarSim vs DiffCloth · T-shirt under 3 discretisationsfull Chamfer distance dC: 0.020 -> 0.009 (M1,M2); 0.021 -> 0.009 (M1,M3)Improved
swap input representation between UDF, point cloud, 3D Gaussians and mesh (ablation)NeuralGarSim · garment simulationcross-modal Chamfer distance: dW 0.017 (UDF), 0.017 (Gaussians); dC 0.013, 0.014No clear effect
replace TDC with per-panel UV parameterisation and 3D input (NeuralClothSim+) with non-conformal parameterisation (ablation)NeuralClothSim+ · multi-panel garmentconvergenceHurt
use conformal parameterisation in the NeuralClothSim+ extension (ablation)NeuralClothSim+ · multi-panel garmentdrape plausibilityNo clear effect

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