基于人脸部件掩膜的自监督三维人脸重建  

Self-supervised 3D Face Reconstruction Based on Detailed Face Mask

作　　者：朱磊[1] 王善敏[2] 刘青山[1] ZHU Lei;WANG Shanmin;LIU Qingshan(Engineering Research Center of Digital Forensics,Ministry of Education,Nanjing University of Information Science,Technology,Nanjing 210044,China;College of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China)

机构地区：[1]南京信息工程大学数字取证教育部研究中心,南京210044 [2]南京航空航天大学计算机学院,南京210016

出　　处：《计算机科学》2023年第2期214-220,共7页Computer Science

基　　金：国家杰出青年基金(61825601)。

摘　　要：三维人脸重建旨在从二维人脸图片中恢复出三维人脸模型。自监督三维人脸重建能够缓解三维人脸数据缺乏的问题,因此成为了近年来的研究热点。现有的自监督方法通常聚焦于使用全局监督信号,对人脸的局部细节关注不足。为了更好地恢复出细节生动的精细化三维人脸,提出了一种基于人脸部件掩膜的精细化三维人脸重建方法,该方法在不需要任何三维人脸标注的情况下,可以重建出精细化三维人脸。其主要思想是在二维图片一致性损失、图片深层感知损失等基本损失函数上,通过人脸部件掩膜,给予人脸区域精细化约束,并对人脸部件掩膜进行自监督约束,从而提高重建的三维人脸局部的准确性。在AFLW2000-3D和MICC Florence数据集上进行了定性以及定量实验,验证了所提方法的有效性和优越性。Self-supervised 3D face reconstruction can alleviate the problem of lack of 3D face data,and has therefore become a hot research topic in recent years.Existing self-supervised methods usually focus on using globally supervised signals and do not pay enough attention to the local details of faces.In order to better recover fine-grained 3D faces with vivid details,this paper proposes a fine-grained 3D face reconstruction method based on face part masks,which can reconstruct fine-grained 3D faces without any 3D face annotation.The main idea is to improve the local accuracy of the reconstructed 3D face by giving refinement constraints on the face region through the face part mask and self-supervised constraints on the face part mask on top of the basic loss functions such as 2D image consistency loss,image deep perception loss,etc.Qualitative and quantitative experiments on AFLW2000-3D and MICC Florence datasets demonstrate the effectiveness and superiority of the proposed method.

关 键 词：三维人脸重建 人脸对齐 人脸建模 自监督学习 人脸渲染 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]