智能系统学报2023，Vol.18Issue(6)：1173-1184,12.DOI:10.11992/tis.202304011
融合分层特征与残差蒸馏连接的图像超分辨率重建
Image super-resolution reconstruction by fusing layered features with residual distillation connections
摘要
Abstract
Aiming at the issue that several current image super-resolution reconstruction algorithms cannot fully utilize the feature information by adopting a single-channel network structure,a super-resolution reconstruction algorithm that fuses hierarchical features and residual distillation connections is proposed.In this method,a connection method that combines layered features with residual connections is adopted to fully fuse the deep and shallow features of an image,improving the utilization of feature information by the network.Further,a residual distillation attention module is used,which enables the network to focus on the key features of the image efficiently,allowing efficient recovery of the de-tailed features of the reconstructed image.The experimental results showed that the proposed algorithmic model exhib-its better objective evaluation indexes on four test sets and has a superior reconstruction effect on the subjective visual effect.Specifically,on the Set14 test set,the peak signal-to-noise ratio of the four-fold reconstruction results of the mod-el is improved by 0.85 dB on average relative to the comparison model and the structural similarity is improved by 0.034 on average,demonstrating the effectiveness of the algorithmic model.关键词
图像处理/超分辨率重建/U型网络/残差连接/神经网络/特征融合/注意力机制/亚像素卷积Key words
image processing/super-resolution reconstruction/U-network/residual connectivity/neural network/fea-ture fusion/attention mechanism/subpixel convolution分类
计算机与自动化引用本文复制引用
程德强,朱星光,寇旗旗,陈亮亮,王晓艺,赵佳敏..融合分层特征与残差蒸馏连接的图像超分辨率重建[J].智能系统学报,2023,18(6):1173-1184,12.基金项目
中央高校基本科研业务费专项资金项目(2020QN49) （2020QN49）
国家自然科学基金项目(52204177). （52204177）
