非人形生物模仿人类的表演

ACM SIGGRAPH 2016 Posters Pub Date : 2016-07-24 DOI:10.1145/2945078.2945080

Gustavo Eggert Boehs, M. Vieira

{"title":"非人形生物模仿人类的表演","authors":"Gustavo Eggert Boehs, M. Vieira","doi":"10.1145/2945078.2945080","DOIUrl":null,"url":null,"abstract":"We propose a framework for using human acting as input for the animation of non-humanoid creatures; captured motion is classified using machine learning techniques, and a combination of preexisting clips and motion retargeting are used to synthetize new motions. This should lead to a broader use of motion capture.","PeriodicalId":417667,"journal":{"name":"ACM SIGGRAPH 2016 Posters","volume":"63 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Non-humanoid creature performance from human acting\",\"authors\":\"Gustavo Eggert Boehs, M. Vieira\",\"doi\":\"10.1145/2945078.2945080\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose a framework for using human acting as input for the animation of non-humanoid creatures; captured motion is classified using machine learning techniques, and a combination of preexisting clips and motion retargeting are used to synthetize new motions. This should lead to a broader use of motion capture.\",\"PeriodicalId\":417667,\"journal\":{\"name\":\"ACM SIGGRAPH 2016 Posters\",\"volume\":\"63 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-07-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACM SIGGRAPH 2016 Posters\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/2945078.2945080\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM SIGGRAPH 2016 Posters","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2945078.2945080","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

我们提出了一个使用人类行为作为非人形生物动画输入的框架;使用机器学习技术对捕获的运动进行分类，并使用预先存在的剪辑和运动重新定位的组合来合成新的运动。这将导致更广泛的使用动作捕捉。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Non-humanoid creature performance from human acting

We propose a framework for using human acting as input for the animation of non-humanoid creatures; captured motion is classified using machine learning techniques, and a combination of preexisting clips and motion retargeting are used to synthetize new motions. This should lead to a broader use of motion capture.

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

ACM SIGGRAPH 2016 Posters

自引率

0.00%

发文量