改进多层级特征损失及全局注意力的三维人脸重建算法  

Three-dimensional facial reconstruction algorithm based on enhanced multi-level feature loss and global attention

作　　者：何亚岚 魏国亮 武俊珂 HE Yalan;WEI Guoliang;WU Junke(College of Science,University of Shanghai for Science and Technology,Shanghai 200093,China;Business School,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学理学院,上海200093 [2]上海理工大学管理学院,上海200093

出　　处：《上海理工大学学报》2025年第1期89-99,共11页Journal of University of Shanghai For Science and Technology

基　　金：国家自然科学基金资助项目(62273239)。

摘　　要：针对人脸重建算法在细节重建能力、精度以及遮挡影响方面存在的不足,提出一种改进多层级特征损失及全局注意力的三维人脸重建算法。在输入层添加人脸关键点与遮罩的面部先验信息,引导模型关注人脸的重要区域;设计了全局感知金字塔注意力模块,增强模型对重要特征的关注程度,同时充分融合不同层级的特征信息;提出人脸掩膜一致性损失与结构一致性损失,并设计多层级特征损失对模型进行训练优化,提升算法对遮挡情况的重建稳健性,并使输入图像与重建结果在结构上更趋近于一致,丰富模型的特征表示。实验结果表明,重建出的人脸模型具有更多的细节特征,显著增强了遮挡情况下的面部细节重建效果,大幅提高了现有方法的重建精度与鲁棒性能。Aiming at the shortcomings of facial reconstruction algorithms in terms of detail reconstruction capability,accuracy,and the impact of occlusions,a three-dimensional facial reconstruction algorithm was proposed,incorporating improved multi-level feature loss and global attention.Facial landmarks and facial mask priors were added at the input layer to guide the model to focus on the important facial regions.The global relation-aware pyramid attention module was designed to enhance the model's attention to important features and effectively integrate feature information from different levels.The face mask consistency loss and structural consistency loss were introduced,and the multi-level feature losses were designed to optimize model training,improve robustness to occlusions,make the input image and the reconstructed result approach each other in terms of structure,and enrich the feature representation of the model.Experimental results demonstrate that the reconstructed facial model exhibites more detailed features,significantly enhances facial detail reconstruction under occlusions,and greatly improves the reconstruction accuracy and robustness of existing methods.

关 键 词：三维人脸重建 深度学习 人脸建模 三维形变模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]