Shape Augmented Regression for 3D Face Alignment
Gou, Chao4,6; Wu, Yue5; Wang FY(王飞跃)4,6; Ji, Qiang5
2016-10
会议名称ECCV 2016 Workshops
会议录名称ECCV 2016 Workshops
会议日期2016.10
会议地点Amsterdam, Netherlands
摘要
2D face alignment has been an active topic and is becoming mature for real applications. However, when large head pose exists, 2D annotated points lose geometric correspondence with respect to actual 3D location. In addition, local appearance varies more dramatically when subjects are with large pose or under various illuminations. 3D face alignment from 2D images is a promising solution to tackle this problem. 3D face alignment aims to estimate the 3D face shape which is consistent across all poses. In this paper, we propose a novel 3D face alignment method. This method consists of two steps. First, we perform 2D landmark detection based on the shape augmented regression. Second, we estimate the 3D shape using the detected 2D landmarks and 3D deformable model. Experimental results on benchmark database demonstrate its preferable performances.
关键词Shape Augmented Regression 3d Face Alignment
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/14486
专题复杂系统管理与控制国家重点实验室_平行智能技术与系统团队
通讯作者Gou, Chao
作者单位1.中国科学院自动化研究所
2.Rensselaer Polytechnic Institute
3.Qingdao Academy of Intelligent Industries
4.中国科学院自动化研究所
5.Rensselaer Polytechnic Institute
6.Qingdao Academy of Intelligent Industries
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
Gou, Chao,Wu, Yue,Wang FY,et al. Shape Augmented Regression for 3D Face Alignment[C],2016.
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
gouc_ECCVW_2016_shap(5239KB)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
[Gou, Chao]的文章
[Wu, Yue]的文章
[Wang FY(王飞跃)]的文章
百度学术
百度学术中相似的文章
[Gou, Chao]的文章
[Wu, Yue]的文章
[Wang FY(王飞跃)]的文章
必应学术
必应学术中相似的文章
[Gou, Chao]的文章
[Wu, Yue]的文章
[Wang FY(王飞跃)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: gouc_ECCVW_2016_shape augmented for 3D face alignment.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。