Core Concepts
Proposing a Bayesian Differentiable Physics model for accurate cloth digitalization from limited data samples.
Stats
"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."
"Our model enables the generalization of the learned mechanical characteristics and materials to garments."
Quotes
"We propose a new method for cloth digitalization."
"Our model enables the generalization of the learned mechanical characteristics and materials to garments."