A Unified Multi-output Semi-supervised Network for 3D Face Reconstruction
Wang, Pengrui1,2; Tian, Yi1,3; Che, Wujun1; Xu, Bo1
2019-07
会议名称International Joint Conference on Neural Networks (IJCNN)
会议日期2019-07
会议地点Budapest
摘要

In this paper, we propose a method to reconstruct fine-grained 3D faces from single images base on a nearly unified multi-output regression network. The network estimates the facial shape, normal and appearance jointly in 2D UV map which preserves spatial adjacency relations among vertexes and provides  semantic meaning of each vertex. Three contributions of the proposed method are: 1) we generate the UV map by as-rigid-as-possible parametrization to address the overlapping problem caused by cylindrical unwarp; 2) we directly estimate face normal rather than compute it from the estimated shape to let it catch geometric details from face texture; 3) we propose a post process strategy to generating more realistic faces and to employing the estimated normal. Experiments show that our network is able to learn a uniform appearance and predict more accurate shape from the proposed UV map. Additionally, the post process procedure can improve the quality of facial shapes and add geometric details from estimated normals.

收录类别EI
资助项目National Key RD Plan of China[2017YFB1002804]
语种英语
七大方向——子方向分类计算机图形学与虚拟现实
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/40396
专题数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者Che, Wujun
作者单位1.Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.Hunan Normal University, China
3.University of Chinese Academy of Sciences, China
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Wang, Pengrui,Tian, Yi,Che, Wujun,et al. A Unified Multi-output Semi-supervised Network for 3D Face Reconstruction[C],2019.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
PID5841719.pdf(1744KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang, Pengrui]的文章
[Tian, Yi]的文章
[Che, Wujun]的文章
百度学术
百度学术中相似的文章
[Wang, Pengrui]的文章
[Tian, Yi]的文章
[Che, Wujun]的文章
必应学术
必应学术中相似的文章
[Wang, Pengrui]的文章
[Tian, Yi]的文章
[Che, Wujun]的文章
相关权益政策
暂无数据
收藏/分享
文件名: PID5841719.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。