二阶逐层特征融合网络的图像超分辨重建  

Second-order progressive feature fusion network for image super-resolution reconstruction

作　　者：于蕾[1] 邓秋月 郑丽颖[2] 吴昊宇 YU Lei;DENG Qiuyue;ZHENG Liying;WU Haoyu(School of Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China;School of Computer Science and Technology,Harbin Engineering University,Harbin 150001,China)

机构地区：[1]哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001 [2]哈尔滨工程大学计算机科学与技术学院,黑龙江哈尔滨150001

出　　处：《系统工程与电子技术》2024年第2期391-400,共10页Systems Engineering and Electronics

基　　金：国家自然科学基金(61771155)资助课题。

摘　　要：针对一些超分辨网络忽略了对网络各层次特征的复用以及融合的问题,构建了具有较强特征复用和融合能力的二阶逐层特征融合超分辨网络,以获得具有高分辨率、高保真度的重建图像。网络的核心是逐层特征融合模块,该模块通过特征融合操作增强特征的重用。此外,还提出了二阶特征融合机制,该机制在网络的局部和全局层次上采用逐层特征融合方法进行特征融合。实验结果表明该网络的重建图像在线条和轮廓上更清晰,并且在峰值信噪比和结构相似度上也取得了更好的结果。例如当缩放尺度因子为2时,各测试集上的峰值信噪比/结构相似度依次为38.20 dB/0.9612、33.81 dB/0.9195、32.28 dB/0.9010、32.65 dB/0.9324、39.11 dB/0.9779,相比其他模型有一定提升,从客观标准和主观角度证明了二阶逐层特征融合超分辨网络具有一定的优越性。Some super-resolution networks ignore the reuse of the features of different levels,and there is no fusing of the features.In order to solve those problems,a second-order progressive feature fusion super-resolution network with strong feature reuse and fuse ability is constructed to realize the reconstructed image with high resolution and high fidelity.The core of the network is progressive feature fusion block.Progressive feature fusion block enhances the reuse of features through feature fusion operation.In addition,a second-order feature fusion mechanism is proposed,which adopts progressive feature fusion method for feature fusion at the local and global levels of the network.The experimental results show that the reconstructed image of the network is clearer than that of other networks on line and contour,and better results are obtained in peak signal to noise ratio(SNR)and structural similarity.For example,when the scaling factor is 2,the peak SNR/structure similarity on each test set is 38.20 dB/0.9612,33.81 dB/0.9195,32.28 dB/0.9010,32.65 dB/0.9324,and 39.11 dB/0.9779 respectively,which proves that the proposed model acheives improvent compared to other models.The advantages of the second-order progressive feature fusion super-resolution network is proven from the objective standard and subjective point of view.

关 键 词：超分辨重建 卷积神经网络 特征融合 二阶特征融合机制 

分 类 号：TN911.73[电子电信—通信与信息系统]