Bayesian Differentiable Physics for Cloth Digitalization
This work addresses cloth digitalization for applications like virtual try-on and simulation, but it is incremental as it builds on existing differentiable physics methods with a new dataset and Bayesian approach.
The authors tackled cloth digitalization by learning from a new dataset captured under strict measuring protocols, proposing a Bayesian differentiable cloth model that achieves accurate digitalization from very limited data samples, with results showing high accuracy and efficiency.
We propose a new method for cloth digitalization. Deviating from existing methods which learn from data captured under relatively casual settings, we propose to learn from data captured in strictly tested measuring protocols, and find plausible physical parameters of the cloths. However, such data is currently absent, so we first propose a new dataset with accurate cloth measurements. Further, the data size is considerably smaller than the ones in current deep learning, due to the nature of the data capture process. To learn from small data, we propose a new Bayesian differentiable cloth model to estimate the complex material heterogeneity of real cloths. It can provide highly accurate digitalization from very limited data samples. Through exhaustive evaluation and comparison, we show our method is accurate in cloth digitalization, efficient in learning from limited data samples, and general in capturing material variations. Code and data are available https://github.com/realcrane/Bayesian-Differentiable-Physics-for-Cloth-Digitalization