Authors: Eunjung Ju1, Eungjune Shim1, Kwang-yun Kim1, Sungjin Yoon1, Myung Geol Choi2
1CLO Virtual Fashion Inc., Seoul, South Korea | 2 The Catholic University of Korea, Bucheon, South Korea
We present a cloth simulation parameter estimation method that integrates the flexibility of global optimization with the speed of neural networks. While global optimization allows for varied designs in objective functions and specifying the range of optimization variables, it requires thousands of objective function evaluations. Each evaluation, which involves a cloth simulation, is computationally demanding and impractical time-wise. On the other hand, neural network learning methods offer quick estimation results but face challenges such as the need for data collection, re-training when input data formats change, and difficulties in setting constraints on variable ranges. Our proposed method addresses these issues by replacing the simulation process, typically necessary for objective function evaluations in global optimization, with a neural network for inference. We demonstrate that, once an estimation model is trained, optimization for various objective functions becomes straightforward. Moreover, we illustrate that it is possible to achieve optimization results that reflect the intentions of expert users through visualization of a wide optimization space and the use of range constraints.
@article{Ju2024ClothOptimization,
author = {Eunjung Ju and Eungjune Shim and Kwang-yun Kim and Sungjin Yoon and Myung Geol Choi},
title = {Fast Constrained Optimization for Cloth Simulation Parameters from Static Drapes},
journal = {Computer Animation and Virtual Worlds},
volume = {35},
year = {2024},
number = {3},
pages = {e2265},
doi = {10.1002/cav.2265},
publisher = {John Wiley & Sons Ltd}
}