使用神经网络的面部重定向

T. Costigan, Mukta Prasad, R. Mcdonnell
{"title":"使用神经网络的面部重定向","authors":"T. Costigan, Mukta Prasad, R. Mcdonnell","doi":"10.1145/2668064.2668099","DOIUrl":null,"url":null,"abstract":"Mapping the motion of an actor's face to a virtual model is a difficult but important problem, especially as fully animated characters are becoming more common in games and movies. Many methods have been proposed but most require the source and target to be structurally similar. Optical motion capture markers and blendshape weights are an example of topologically incongruous source and target examples that do not have a simple mapping between one another. In this paper, we created a system capable of determining this mapping through supervised learning of a small training dataset. Radial Basis Function Networks (RBFNs) have been used for retargeting markers to blendshape weights before but to our knowledge Multi-Layer Perceptron Artificial Neural Networks (referred to as ANNs) have not been employed in this way. We hypothesized that ANNs would result in a superior retargeting solution compared to the RBFN, due to their theoretically greater representational power. We implemented a retargeting system using ANNs and RBFNs for comparison. Our results found that both systems produced similar results (figure 1) and in some cases the ANN proved to be more expressive although the ANN was more difficult to work with.","PeriodicalId":138747,"journal":{"name":"Proceedings of the 7th International Conference on Motion in Games","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"Facial retargeting using neural networks\",\"authors\":\"T. Costigan, Mukta Prasad, R. Mcdonnell\",\"doi\":\"10.1145/2668064.2668099\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Mapping the motion of an actor's face to a virtual model is a difficult but important problem, especially as fully animated characters are becoming more common in games and movies. Many methods have been proposed but most require the source and target to be structurally similar. Optical motion capture markers and blendshape weights are an example of topologically incongruous source and target examples that do not have a simple mapping between one another. In this paper, we created a system capable of determining this mapping through supervised learning of a small training dataset. Radial Basis Function Networks (RBFNs) have been used for retargeting markers to blendshape weights before but to our knowledge Multi-Layer Perceptron Artificial Neural Networks (referred to as ANNs) have not been employed in this way. We hypothesized that ANNs would result in a superior retargeting solution compared to the RBFN, due to their theoretically greater representational power. We implemented a retargeting system using ANNs and RBFNs for comparison. Our results found that both systems produced similar results (figure 1) and in some cases the ANN proved to be more expressive although the ANN was more difficult to work with.\",\"PeriodicalId\":138747,\"journal\":{\"name\":\"Proceedings of the 7th International Conference on Motion in Games\",\"volume\":\"28 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-11-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 7th International Conference on Motion in Games\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/2668064.2668099\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 7th International Conference on Motion in Games","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2668064.2668099","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 11

摘要

将演员的面部动作映射到虚拟模型上是一个困难但重要的问题,尤其是当完全动画的角色在游戏和电影中变得越来越普遍时。已经提出了许多方法,但大多数方法要求源和目标结构相似。光学运动捕捉标记和混合形状权重是拓扑不协调的源和目标示例的一个例子,它们彼此之间没有简单的映射。在本文中,我们创建了一个能够通过小型训练数据集的监督学习来确定这种映射的系统。径向基函数网络(rbfn)以前被用于重定向标记物以混合形状权重,但据我们所知,多层感知器人工神经网络(简称ann)尚未以这种方式使用。我们假设,与RBFN相比,人工神经网络将产生更好的重定向解决方案,因为它们在理论上具有更大的代表性。我们使用人工神经网络和rbfn实现了一个重定向系统进行比较。我们的结果发现,这两个系统产生了相似的结果(图1),在某些情况下,人工神经网络被证明更具表现力,尽管人工神经网络更难使用。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Facial retargeting using neural networks
Mapping the motion of an actor's face to a virtual model is a difficult but important problem, especially as fully animated characters are becoming more common in games and movies. Many methods have been proposed but most require the source and target to be structurally similar. Optical motion capture markers and blendshape weights are an example of topologically incongruous source and target examples that do not have a simple mapping between one another. In this paper, we created a system capable of determining this mapping through supervised learning of a small training dataset. Radial Basis Function Networks (RBFNs) have been used for retargeting markers to blendshape weights before but to our knowledge Multi-Layer Perceptron Artificial Neural Networks (referred to as ANNs) have not been employed in this way. We hypothesized that ANNs would result in a superior retargeting solution compared to the RBFN, due to their theoretically greater representational power. We implemented a retargeting system using ANNs and RBFNs for comparison. Our results found that both systems produced similar results (figure 1) and in some cases the ANN proved to be more expressive although the ANN was more difficult to work with.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信