Image2Garment: Simulation-ready Garment Generation from a Single Image
This addresses the challenge of creating physically accurate garments for applications like virtual try-on or animation, though it is incremental as it builds on prior work by adding material property prediction.
The paper tackles the problem of generating simulation-ready garments from a single image by proposing a feed-forward framework that infers material composition and fabric attributes, then maps them to physical parameters, achieving higher-fidelity simulations compared to state-of-the-art methods.
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.