结合图卷积网络的弱监督三维人脸重建方法  

WEAKLY SUPERVISED 3D FACE RECONSTRUCTION METHOD COMBINED WITH GRAPH CONVOLUTIONAL NETWORK

作　　者：常高祥 刘大明 陈宗民 李冉冉 梁登玉 Chang Gaoxiang;Liu Daming;Chen Zongmin;Li Ranran;Liang Dengyu(School of Computer Science and Technology,Shanghai University of Electric Power,Shanghai 200090,China)

机构地区：[1]上海电力大学计算机科学与技术学院,上海200090

出　　处：《计算机应用与软件》2025年第1期197-204,共8页Computer Applications and Software

基　　金：甘肃省自然科学基金项目(SKLLDJ032016021)。

摘　　要：针对目前深度学习方法在三维人脸重建任务中存在的训练数据不足、重建纹理不够真实等问题,提出一种弱监督混合模型。利用单幅二维人脸图像,通过密集连接卷积网络(DenseNet)回归人脸三维形变模型(3DMM)系数,结合不同层级的特征差异作为弱监督信号,进而提高模型泛化能力。在此基础上使用图卷积网络(GCN)提取输入图像的面部细节特征来优化重建纹理。实验结果表明,该方法可以在无训练标签的数据下重建出精细的人脸三维模型,在归一化平均误差等指标上优于现有方法。In order to solve the problems of insufficient training data and unreal texture in the current deep learning methods in 3D face reconstruction,a weak supervised hybrid model is proposed.Using a single two-dimensional face image,the face 3D deformation model(3DMM)coefficients were regressed by densely connected convolution network(DenseNet),and the feature differences of different levels were used as weak supervision signals to improve the generalization ability of the model.On this basis,the image convolution network(GCN)was used to extract the facial detail features of the input image to optimize the reconstruction texture.The experimental results show that this method can reconstruct the fine three-dimensional model of human face without training label,and is better than the existing methods in terms of normalized average error.

关 键 词：三维人脸重建 弱监督 密集连接卷积网络 三维形变模型 图卷积网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]