中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Fully Automatic Facial Deformation Transfer

文献类型:期刊论文

作者Bian, Shaojun1,2; Zheng, Anzong1,2; Gao, Lin3; Maguire, Greg1,4; Kokke, Willem1; Macey, Jon2; You, Lihua2; Zhang, Jian J.2
刊名SYMMETRY-BASEL
出版日期2020
卷号12期号:1页码:10
关键词face landmark detection orthographic projection point-wise correspondences automatic deformation transfer
DOI10.3390/sym12010027
英文摘要Facial Animation is a serious and ongoing challenge for the Computer Graphic industry. Because diverse and complex emotions need to be expressed by different facial deformation and animation, copying facial deformations from existing character to another is widely needed in both industry and academia, to reduce time-consuming and repetitive manual work of modeling to create the 3D shape sequences for every new character. But transfer of realistic facial animations between two 3D models is limited and inconvenient for general use. Modern deformation transfer methods require correspondences mapping, in most cases, which are tedious to get. In this paper, we present a fast and automatic approach to transfer the deformations of the facial mesh models by obtaining the 3D point-wise correspondences in the automatic manner. The key idea is that we could estimate the correspondences with different facial meshes using the robust facial landmark detection method by projecting the 3D model to the 2D image. Experiments show that without any manual labelling efforts, our method detects reliable correspondences faster and simpler compared with the state-of-the-art automatic deformation transfer method on the facial models.
资助项目Innovate UK[KTP010860] ; EU[H2020-MSCA-RISE-2017-778035] ; China Scholarship Council
WOS研究方向Science & Technology - Other Topics
语种英语
WOS记录号WOS:000516823700027
出版者MDPI
源URL[http://119.78.100.204/handle/2XEOYT63/14006]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Bian, Shaojun
作者单位1.Humain Ltd, Belfast BT1 2LA, Antrim, North Ireland
2.Bournemouth Univ, Natl Ctr Comp Animat, Poole BH12 5BB, Dorset, England
3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
4.Ulster Univ, Belfast Sch Art, York St, Belfast BT15 1ED, Antrim, North Ireland
推荐引用方式
GB/T 7714
Bian, Shaojun,Zheng, Anzong,Gao, Lin,et al. Fully Automatic Facial Deformation Transfer[J]. SYMMETRY-BASEL,2020,12(1):10.
APA Bian, Shaojun.,Zheng, Anzong.,Gao, Lin.,Maguire, Greg.,Kokke, Willem.,...&Zhang, Jian J..(2020).Fully Automatic Facial Deformation Transfer.SYMMETRY-BASEL,12(1),10.
MLA Bian, Shaojun,et al."Fully Automatic Facial Deformation Transfer".SYMMETRY-BASEL 12.1(2020):10.

入库方式: OAI收割

来源:计算技术研究所

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。