Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.09658 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911527516241920 |
|---|---|
| author | Can, Selim Emir Ackermann, Jan Nakayama, Kiyohiro Liu, Ruofan Wu, Tong Zheng, Yang Bertiche, Hugo Chai, Menglei Beeler, Thabo Wetzstein, Gordon |
| author_facet | Can, Selim Emir Ackermann, Jan Nakayama, Kiyohiro Liu, Ruofan Wu, Tong Zheng, Yang Bertiche, Hugo Chai, Menglei Beeler, Thabo Wetzstein, Gordon |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_09658 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Image2Garment: Simulation-ready Garment Generation from a Single Image Can, Selim Emir Ackermann, Jan Nakayama, Kiyohiro Liu, Ruofan Wu, Tong Zheng, Yang Bertiche, Hugo Chai, Menglei Beeler, Thabo Wetzstein, Gordon Computer Vision and Pattern Recognition 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. |
| title | Image2Garment: Simulation-ready Garment Generation from a Single Image |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.09658 |