期刊
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
卷 -, 期 -, 页码 8130-8140出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR52688.2022.00797
关键词
-
资金
- European Research Council (ERC Consolidator Grant) [772738]
- Spanish Ministry of Science [RTI2018-098694-B-I00]
- European Research Council (ERC) [772738] Funding Source: European Research Council (ERC)
This article presents a self-supervised method for learning dynamic 3D deformations of garments worn by parametric human bodies. By formulating an optimization problem and using physics-based loss terms, neural networks can be trained without precomputing ground-truth data, resulting in a significant speed up in training time.
We present a self-supervised method to learn dynamic 3D deformations of garments worn by parametric human bodies. State-of-the-art data-driven approaches to model 3D garment deformations are trained using supervised strategies that require large datasets, usually obtained by expensive physics-based simulation methods or professional multi-camera capture setups. In contrast, we propose a new training scheme that removes the need for ground-truth samples, enabling self-supervised training of dynamic 3D garment deformations. Our key contribution is to realize that physics-based deformation models, traditionally solved in a frame-by-frame basis by implicit integrators, can be recasted as an optimization problem. We leverage such optimization-based scheme to formulate a set of physics-based loss terms that can be used to train neural networks without precomputing ground-truth data. This allows us to learn models for interactive garments, including dynamic deformations and fine wrinkles, with a two orders of magnitude speed up in training time compared to state-of-the-art supervised methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据