面向人脸图像超分辨率重建的CNN-Mamba属性引导网络  

Attribute-guided Network Based on CNN-Mamba for Super-resolution Reconstruction of Face Images

作　　者：刘晓亚 韦姿煜 周迪 宋廷强[1] 孙媛媛[1] LIU Xiao-Ya;WEI Zi-Yu;ZHOU Di;SONG Ting-Qiang;SUN Yuan-Yuan(School of Data Science,Qingdao University of Science and Technology,Qingdao 266061,China)

机构地区：[1]青岛科技大学数据科学学院,青岛266061

出　　处：《计算机系统应用》2025年第3期124-132,共9页Computer Systems & Applications

基　　金：国家自然科学基金(32301702);山东省自然科学基金(ZR2021QC120)。

摘　　要：针对现有的方法通常面临全局感受野和高效计算之间难以有效平衡以及重建图像细节不清晰的问题,提出了基于CNN-Mamba的属性引导网络(CMANet).首先,模型在进行重建时,引入了属性信息并且考虑了这些属性之间的相互关系,帮助模型提高整个重建过程的可靠性和精确度.其次,引入了沙漏状态空间模块,发掘人脸图像的关键特征,并保持了在长距离依赖建模方面具有线性复杂度的优势.最后,引入了自适应Mamba融合模块,在图像特征学习多个方向长距离依赖关系时,将属性针对不同方向进行自适应补充,并将不同方向补充后的特征进行自适应融合,使得模型在处理多样化的图像时更加灵活和高效.大量的实验证明了所提方法的优越性.Aiming at the difficult balance between the global receptive field and efficient computation and unclear details of image reconstruction,an attribute guided network based on CNN-Mamba(CMANet)is proposed.Firstly,when the model is reconstructed,attribute information is introduced and interrelationships among these attributes are considered,which helps the model to improve the reliability and accuracy of the whole reconstruction process.Secondly,the hourglass state space module is introduced to explore the key features of face images and maintain the advantage of linear complexity in long-distance dependency modeling.Finally,an adaptive Mamba fusion module is introduced.When image features learn long-distance dependencies in multiple directions,attributes are adaptively supplemented in different directions,and features supplemented in different directions are adaptively fused,making the model more flexible and efficient in processing diverse images.A large number of experiments prove the superiority of the proposed method.

关 键 词：人脸图像 属性 超分辨率重建 状态空间模块 图注意力网络 自注意力机制 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]