Optical flow estimation in human facial video,which provides 2D correspondences between adjacent frames,is a fundamental pre-processing step for many applications,like facial expression capture and recognition.However...Optical flow estimation in human facial video,which provides 2D correspondences between adjacent frames,is a fundamental pre-processing step for many applications,like facial expression capture and recognition.However,it is quite challenging as human facial images contain large areas of similar textures,rich expressions,and large rotations.These characteristics also result in the scarcity of large,annotated realworld datasets.We propose a robust and accurate method to learn facial optical flow in a self-supervised manner.Specifically,we utilize various shape priors,including face depth,landmarks,and parsing,to guide the self-supervised learning task via a differentiable nonrigid registration framework.Extensive experiments demonstrate that our method achieves remarkable improvements for facial optical flow estimation in the presence of significant expressions and large rotations.展开更多
三维人脸稠密对应是三维人脸分析研究的前提和基础。目前大多数的稠密对应技术是基于模板形变的方式,非刚性最近点迭代(iterative closest point, ICP)是应用最为广泛的一种,该算法通过逐步形变一个高分辨率的三维人脸模板来逼近目标人...三维人脸稠密对应是三维人脸分析研究的前提和基础。目前大多数的稠密对应技术是基于模板形变的方式,非刚性最近点迭代(iterative closest point, ICP)是应用最为广泛的一种,该算法通过逐步形变一个高分辨率的三维人脸模板来逼近目标人脸(扫描人脸数据)。但该类方法通过牺牲边缘精度来保持边缘区域的拓扑结构,以保证人脸之间的稠密对应。针对这一问题,提出了一种结合拓扑结构损失项的非刚性ICP算法,使得保持边缘区域拓扑结构的同时不会大幅度牺牲配准精度。实验结果表明,该算法比目前广泛使用的算法配准精度更高。展开更多
A 3D face recognition approach which uses principal axes registration(PAR)and three face representation features from the re-sampling depth image:Eigenfaces,Fisherfaces and Zernike moments is presented.The approach ad...A 3D face recognition approach which uses principal axes registration(PAR)and three face representation features from the re-sampling depth image:Eigenfaces,Fisherfaces and Zernike moments is presented.The approach addresses the issue of 3D face registration instantly achieved by PAR.Because each facial feature has its own advantages,limitations and scope of use,different features will complement each other.Thus the fusing features can learn more expressive characterizations than a single feature.The support vector machine(SVM)is applied for classification.In this method,based on the complementarity between different features,weighted decision-level fusion makes the recognition system have certain fault tolerance.Experimental results show that the proposed approach achieves superior performance with the rank-1 recognition rate of 98.36%for GavabDB database.展开更多
基金This work was supported by National Natural Science Foundation of China(No.62122071)the Youth Innovation Promotion Association CAS(No.2018495)+1 种基金the Fundamental Research Funds for the Central Universities(No.WK3470000021)through the Alibaba Innovation Research Program(AIR).
文摘Optical flow estimation in human facial video,which provides 2D correspondences between adjacent frames,is a fundamental pre-processing step for many applications,like facial expression capture and recognition.However,it is quite challenging as human facial images contain large areas of similar textures,rich expressions,and large rotations.These characteristics also result in the scarcity of large,annotated realworld datasets.We propose a robust and accurate method to learn facial optical flow in a self-supervised manner.Specifically,we utilize various shape priors,including face depth,landmarks,and parsing,to guide the self-supervised learning task via a differentiable nonrigid registration framework.Extensive experiments demonstrate that our method achieves remarkable improvements for facial optical flow estimation in the presence of significant expressions and large rotations.
文摘三维人脸稠密对应是三维人脸分析研究的前提和基础。目前大多数的稠密对应技术是基于模板形变的方式,非刚性最近点迭代(iterative closest point, ICP)是应用最为广泛的一种,该算法通过逐步形变一个高分辨率的三维人脸模板来逼近目标人脸(扫描人脸数据)。但该类方法通过牺牲边缘精度来保持边缘区域的拓扑结构,以保证人脸之间的稠密对应。针对这一问题,提出了一种结合拓扑结构损失项的非刚性ICP算法,使得保持边缘区域拓扑结构的同时不会大幅度牺牲配准精度。实验结果表明,该算法比目前广泛使用的算法配准精度更高。
基金The authors would like to acknowledge the use of the GavabDB face database in this paper due to Moreno and Sanchez.This work was supported in part by the National Natural Science Foundation of China(Grant No.60872145)the National High Technology Research and Development Program of China(No.2009AA01Z315)the Cultivation Fund of the Key Scientific and Technical Innovation Project,Ministry of Education of China(No.708085).
文摘A 3D face recognition approach which uses principal axes registration(PAR)and three face representation features from the re-sampling depth image:Eigenfaces,Fisherfaces and Zernike moments is presented.The approach addresses the issue of 3D face registration instantly achieved by PAR.Because each facial feature has its own advantages,limitations and scope of use,different features will complement each other.Thus the fusing features can learn more expressive characterizations than a single feature.The support vector machine(SVM)is applied for classification.In this method,based on the complementarity between different features,weighted decision-level fusion makes the recognition system have certain fault tolerance.Experimental results show that the proposed approach achieves superior performance with the rank-1 recognition rate of 98.36%for GavabDB database.
