DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact

Li, Yifei; Du, Tao; Wu, Kui; Xu, Jie; Matusik, Wojciech

doi:10.48550/arxiv.2106.05306

Cited by 1 publication

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By combining physically-based cloth simulators and neural networks, Runia et al ( 2020) estimated cloth parameters by training neural networks to adjust a simulator's parameters so that the simulated cloth mimics the observed one in videos. Different from these gradient-free models, Liang et al (2019) and Li et al (2021) proposed sheet-level differentiable cloth models that can be used to estimate cloth parameters. In this work, we dive into fine-grained physics and propose a new yarn-level differentiable fabrics model which can be embedded into deep neural networks as a layer.…”

Section: Related Workmentioning

confidence: 99%

Fine-grained differentiable physics: a yarn-level model for fabrics

Gong¹,

Zhu²,

Bulpitt³

et al. 2022

Preprint

View full text Add to dashboard Cite

Differentiable physics modeling combines physics models with gradient-based learning to provide model explicability and data efficiency. It has been used to learn dynamics, solve inverse problems and facilitate design, and is at its inception of impact. Current successes have concentrated on general physics models such as rigid bodies, deformable sheets, etc, assuming relatively simple structures and forces. Their granularity is intrinsically coarse and therefore incapable of modelling complex physical phenomena. Fine-grained models are still to be developed to incorporate sophisticated material structures and force interactions with gradient-based learning. Following this motivation, we propose a new differentiable fabrics model for composite materials such as cloths, where we dive into the granularity of yarns and model individual yarn physics and yarn-to-yarn interactions. To this end, we propose several differentiable forces, whose counterparts in empirical physics are indifferentiable, to facilitate gradient-based learning. These forces, albeit applied to cloths, are ubiquitous in various physical systems. Through comprehensive evaluation and comparison, we demonstrate our model's explicability in learning meaningful physical parameters, versatility in incorporating complex physical structures and heterogeneous materials, data-efficiency in learning, and high-fidelity in capturing subtle dynamics. Code is available in: https://github.com/realcrane/Fine-grained-Differentiable-P hysics-A-Yarn-level-Model-for-Fabrics.git

show abstract

Section: Related Workmentioning

confidence: 99%