Towards Fine-Grained Optimal 3D Face Dense Registration: An Iterative Dividing and Diffusing Method | |
Fan, Zhenfeng2,3; Peng, Silong1,2; Xia, Shihong2,3 | |
刊名 | INTERNATIONAL JOURNAL OF COMPUTER VISION |
2023-06-03 | |
页码 | 21 |
关键词 | 3D face Dense correspondence Non-rigid registration 3D morphable model |
ISSN号 | 0920-5691 |
DOI | 10.1007/s11263-023-01825-7 |
通讯作者 | Xia, Shihong(xsh@ict.ac.cn) |
英文摘要 | Dense vertex-to-vertex correspondence (i.e. registration) between 3D faces is a fundamental and challenging issue for 3D &2D face analysis. While the sparse landmarks are definite with anatomically ground-truth correspondence, the dense vertex correspondences on most facial regions are unknown. In this view, the current methods commonly result in reasonable but diverse solutions, which deviate from the optimum to the dense registration problem. In this paper, we revisit dense registration by a dimension-degraded problem, i.e. proportional segmentation of a line, and employ an iterative dividing and diffusing method to reach an optimum solution that is robust to different initializations. We formulate a local registration problem for dividing and a linear least-square problem for diffusing, with constraints on fixed features on a 3D facial surface. We further propose a multi-resolution algorithm to accelerate the computational process. The proposed method is linked to a novel local scaling metric, where we illustrate the physical significance as smooth adaptions for local cells of 3D facial shapes. Extensive experiments on public datasets demonstrate the effectiveness of the proposed method in various aspects. Generally, the proposed method leads to not only significantly better representations of 3D facial data, but also coherent local deformations with elegant grid architecture for fine-grained registrations. |
资助项目 | National Key Research and Development Program of China[2022YFF0902302] ; National Science Foundation of China[62106250] ; China Postdoctoral Science Foundation[2021M703272] |
WOS关键词 | POINT ; RECOGNITION ; RECONSTRUCTION ; DATABASE ; TRENDS |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | SPRINGER |
WOS记录号 | WOS:000998738900001 |
资助机构 | National Key Research and Development Program of China ; National Science Foundation of China ; China Postdoctoral Science Foundation |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/53423] |
专题 | 自动化研究所_智能制造技术与系统研究中心_多维数据分析团队 |
通讯作者 | Xia, Shihong |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Fan, Zhenfeng,Peng, Silong,Xia, Shihong. Towards Fine-Grained Optimal 3D Face Dense Registration: An Iterative Dividing and Diffusing Method[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2023:21. |
APA | Fan, Zhenfeng,Peng, Silong,&Xia, Shihong.(2023).Towards Fine-Grained Optimal 3D Face Dense Registration: An Iterative Dividing and Diffusing Method.INTERNATIONAL JOURNAL OF COMPUTER VISION,21. |
MLA | Fan, Zhenfeng,et al."Towards Fine-Grained Optimal 3D Face Dense Registration: An Iterative Dividing and Diffusing Method".INTERNATIONAL JOURNAL OF COMPUTER VISION (2023):21. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论