Image2Garment: Simulation-ready Garment Generation from a Single Image

TL;DR

This paper presents a novel method to generate physically accurate, simulation-ready garments from a single image by inferring material properties and fabric attributes, enabling realistic virtual try-ons without complex multi-view setups.

Contribution

It introduces a new framework that combines vision-language models and a lightweight predictor to estimate fabric parameters from a single image, along with two new datasets for training and evaluation.

Findings

Achieves higher accuracy in material and fabric attribute estimation.

Produces more realistic, simulation-ready garments compared to previous methods.

Avoids iterative optimization, enabling faster garment generation.

Abstract

Estimating physically accurate, simulation-ready garments from a single image is challenging due to the absence of image-to-physics datasets and the ill-posed nature of this problem. Prior methods either require multi-view capture and expensive differentiable simulation or predict only garment geometry without the material properties required for realistic simulation. We propose a feed-forward framework that sidesteps these limitations by first fine-tuning a vision-language model to infer material composition and fabric attributes from real images, and then training a lightweight predictor that maps these attributes to the corresponding physical fabric parameters using a small dataset of material-physics measurements. Our approach introduces two new datasets (FTAG and T2P) and delivers simulation-ready garments from a single image without iterative optimization. Experiments show that our estimator achieves superior accuracy in material composition estimation and fabric attribute prediction, and by passing them through our physics parameter estimator, we further achieve higher-fidelity simulations compared to state-of-the-art image-to-garment methods.