arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.09658cs.CV
收藏

Image2Garment: 从单张图像生成可模拟的服装

Image2Garment: Simulation-ready Garment Generation from a Single Image

Stanford University(斯坦福大学);Google(谷歌);Institute of Science Tokyo(东京科学研究所)

Selim Emir Can, Jan Ackermann, Kiyohiro Nakayama, Ruofan Liu, Tong Wu, Yang Zheng, Hugo Bertiche, Menglei Chai, Thabo Beeler, Gordon Wetzstein

AI总结:

本文提出一种框架,通过微调视觉语言模型获取材料属性,再训练轻量预测模型生成物理参数,实现从单张图像生成可模拟的服装。

摘要:

从单张图像估计物理准确且可模拟的服装具有挑战性,因为缺乏图像到物理的数据库以及该问题的不明确性。先前方法要么需要多视角捕捉和昂贵的可微分模拟,要么只能预测服装几何而无法预测现实模拟所需的材料属性。我们提出了一种前馈框架,通过首先微调视觉语言模型以从真实图像推断材料组成和织物属性,然后训练一个轻量级预测器,利用少量材料-物理测量数据集将这些属性映射到相应的物理织物参数。我们的方法引入了两个新数据集(FTAG和T2P),并实现了从单张图像生成可模拟的服装,而无需迭代优化。实验表明,我们的估计器在材料组成估计和织物属性预测方面具有更高的准确性,通过将这些结果传递给我们的物理参数估计器,我们进一步实现了比现有图像到服装方法更高的仿真保真度。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑