Face Alignment Across Large Poses: A 3D Solution
Zhu XY(朱翔昱)1; Lei Z(雷震)1; Liu XM(刘晓明)2; Shi HL(石海林)1; Li ZQ(李子青)1
2016
会议名称In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
会议日期June 26 - July 1, 2016
会议地点Las Vegas, NV, USA
摘要Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in CV community. However, most algorithms are designed for faces in small to medium poses (below 45 degrees), lacking the ability to align faces in large poses up to 90 degrees. The challenges are three-fold: Firstly, the commonly used landmark-based face model assumes that all the landmarks are visible and is therefore not suitable for profile views. Secondly, the face appearance varies more dramatically across large poses, ranging from frontal view to profile view. Thirdly, labelling landmarks in large poses is extremely challenging since the invisible landmarks have to be guessed. In this paper, we propose a solution to the three problems in an new alignment framework, called 3D Dense Face Alignment (3DDFA), in which a dense 3D face model is fitted to the image via convolutional neutral network (CNN). We also propose a method to synthesize large-scale training samples in profile views to solve the third problem of data labelling. Experiments on the challenging AFLW database show that our approach achieves significant improvements over state-of-the-art methods.
收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/14785
专题模式识别国家重点实验室_生物识别与安全技术研究
作者单位1.中国科学院自动化研究所
2.Department of Computer Science and Engineering, Michigan State University
推荐引用方式
GB/T 7714
Zhu XY,Lei Z,Liu XM,et al. Face Alignment Across Large Poses: A 3D Solution[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
Zhu_Face_Alignment_A(4770KB)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
[Zhu XY(朱翔昱)]的文章
[Lei Z(雷震)]的文章
[Liu XM(刘晓明)]的文章
百度学术
百度学术中相似的文章
[Zhu XY(朱翔昱)]的文章
[Lei Z(雷震)]的文章
[Liu XM(刘晓明)]的文章
必应学术
必应学术中相似的文章
[Zhu XY(朱翔昱)]的文章
[Lei Z(雷震)]的文章
[Liu XM(刘晓明)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Zhu_Face_Alignment_Across_CVPR_2016_paper.pdf
格式: Adobe PDF
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。