中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Face Alignment Across Large Poses: A 3D Solution

文献类型:会议论文

作者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
出版日期2016
会议日期June 26 - July 1, 2016
会议地点Las Vegas, NV, USA
英文摘要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.
源URL[http://ir.ia.ac.cn/handle/173211/14785]  
专题自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心
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]. 见:. Las Vegas, NV, USA. June 26 - July 1, 2016.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

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。