Name
Abstract | ||
|---|---|---|
We propose a differentiable cloth simulator that can be embedded as a layer in deep neural networks. This approach provides an effective, robust framework for modeling cloth dynamics, self-collisions, and contacts. Due to the high dimensionality of the dynamical system in modeling cloth, traditional gradient computation for collision response can become impractical. To address this problem, we propose to compute the gradient directly using QR decomposition of a much smaller matrix. Experimental results indicate that our method can speed up backpropagation by two orders of magnitude. We demonstrate the presented approach on a number of inverse problems, including parameter estimation and motion control for cloth. |
Year | Venue | Keywords |
|---|---|---|
2019 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019) | dynamic system,system dynamics,collision response,motion control,qr decomposition |
Field | DocType | Volume |
Mathematical optimization,Computer science,Differentiable function,Inverse problem | Conference | 32 |
ISSN | Citations | PageRank |
1049-5258 | 2 | 0.37 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jun-Bang Liang | 1 | 16 | 3.93 |
| Ming Lin | 2 | 7046 | 525.99 |
| Vladlen Koltun | 3 | 4064 | 162.63 |