当前位置: X-MOL 学术arXiv.cs.GR › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Realtime Simulation of Thin-Shell Deformable Materials using CNN-Based Mesh Embedding
arXiv - CS - Graphics Pub Date : 2019-09-26 , DOI: arxiv-1909.12354
Qingyang Tan, Zherong Pan, Lin Gao, Dinesh Manocha

We address the problem of accelerating thin-shell deformable object simulations by dimension reduction. We present a new algorithm to embed a high-dimensional configuration space of deformable objects in a low-dimensional feature space, where the configurations of objects and feature points have approximate one-to-one mapping. Our key technique is a graph-based convolutional neural network (CNN) defined on meshes with arbitrary topologies and a new mesh embedding approach based on physics-inspired loss term. We have applied our approach to accelerate high-resolution thin shell simulations corresponding to cloth-like materials, where the configuration space has tens of thousands of degrees of freedom. We show that our physics-inspired embedding approach leads to higher accuracy compared with prior mesh embedding methods. Finally, we show that the temporal evolution of the mesh in the feature space can also be learned using a recurrent neural network (RNN) leading to fully learnable physics simulators. After training our learned simulator runs $500-10000\times$ faster and the accuracy is high enough for robot manipulation tasks.

中文翻译:

使用基于 CNN 的网格嵌入实时模拟薄壳可变形材料

我们解决了通过降维来加速薄壳可变形物体模拟的问题。我们提出了一种新算法,将可变形对象的高维配置空间嵌入到低维特征空间中,其中对象和特征点的配置具有近似的一对一映射。我们的关键技术是在具有任意拓扑结构的网格上定义的基于图的卷积神经网络 (CNN) 和基于物理启发损失项的新网格嵌入方法。我们已应用我们的方法来加速对应于类布材料的高分辨率薄壳模拟,其中配置空间具有数万个自由度。我们表明,与先前的网格嵌入方法相比,我们的受物理启发的嵌入方法具有更高的准确性。最后,我们展示了特征空间中网格的时间演化也可以使用循环神经网络 (RNN) 来学习,从而产生完全可学习的物理模拟器。训练后,我们学习的模拟器运行速度提高了 500-10000\times$,并且精度对于机器人操作任务来说足够高。
更新日期:2020-03-02
down
wechat
bug