基于自监督属性学习的单幅图像精细三维人脸重建

SIGGRAPH Asia 2020 Posters Pub Date : 2020-12-04 DOI:10.1145/3415264.3425455

Mingxin Yang, Jianwei Guo, Juntao Ye, Xiaopeng Zhang

{"title":"基于自监督属性学习的单幅图像精细三维人脸重建","authors":"Mingxin Yang, Jianwei Guo, Juntao Ye, Xiaopeng Zhang","doi":"10.1145/3415264.3425455","DOIUrl":null,"url":null,"abstract":"We present a novel approach to reconstruct high-fidelity geometric human face model from a single RGB image. The main idea is to add details into a coarse 3D Morphable Model (3DMM) based model in a self-supervised way. Our observation is that most of the facial details like wrinkles are driven by expression and intrinsic facial characteristics which here we refer to as the facial attribute. To this end, we propose an expression related details recovery scheme and a facial attribute representation.","PeriodicalId":372541,"journal":{"name":"SIGGRAPH Asia 2020 Posters","volume":"3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Detailed 3D Face Reconstruction from Single Images Via Self-supervised Attribute Learning\",\"authors\":\"Mingxin Yang, Jianwei Guo, Juntao Ye, Xiaopeng Zhang\",\"doi\":\"10.1145/3415264.3425455\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We present a novel approach to reconstruct high-fidelity geometric human face model from a single RGB image. The main idea is to add details into a coarse 3D Morphable Model (3DMM) based model in a self-supervised way. Our observation is that most of the facial details like wrinkles are driven by expression and intrinsic facial characteristics which here we refer to as the facial attribute. To this end, we propose an expression related details recovery scheme and a facial attribute representation.\",\"PeriodicalId\":372541,\"journal\":{\"name\":\"SIGGRAPH Asia 2020 Posters\",\"volume\":\"3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-12-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"SIGGRAPH Asia 2020 Posters\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3415264.3425455\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"SIGGRAPH Asia 2020 Posters","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3415264.3425455","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

提出了一种从单幅RGB图像重构高保真几何人脸模型的新方法。其主要思想是以自监督的方式向基于粗糙3D变形模型(3DMM)的模型中添加细节。我们的观察是，大多数面部细节，如皱纹，是由表情和内在的面部特征驱动的，在这里我们称之为面部属性。为此，我们提出了一种与表情相关的细节恢复方案和面部属性表示。

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

Detailed 3D Face Reconstruction from Single Images Via Self-supervised Attribute Learning

We present a novel approach to reconstruct high-fidelity geometric human face model from a single RGB image. The main idea is to add details into a coarse 3D Morphable Model (3DMM) based model in a self-supervised way. Our observation is that most of the facial details like wrinkles are driven by expression and intrinsic facial characteristics which here we refer to as the facial attribute. To this end, we propose an expression related details recovery scheme and a facial attribute representation.

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

SIGGRAPH Asia 2020 Posters

自引率

0.00%

发文量