###
计算机系统应用英文版:,():1-10
本文二维码信息
码上扫一扫!
基于特征层次递进融合的轻量级图像超分辨率网络
(华北电力大学 控制与计算机工程学院, 北京 102206)
Lightweight Image Super-resolution Network Based on Progressive Fusion of Hierarchical Feature
(School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 8次   下载 314
Received:June 05, 2024    Revised:June 28, 2024
中文摘要: 近年来, 随着深度学习技术的发展, 卷积神经网络(convolutional neural network, CNN)和Transformer在图像超分辨率(super-resolution, SR)领域取得了显著的进展. 但是, 对于图像全局特征的提取, 过去的方法大多采用的是堆叠单个算子重复计算来逐步扩大感受野的方式. 为了更好地利用全局信息, 提出了对局部、区域和全局特征进行显式建模. 具体来说, 通过通道注意增强卷积、基于划分窗口的Transformer和CNN的双分支并行架构、标准的Transformer和划分窗口的Transformer双分支并行架构, 以一种层次递进的方式对图像的局部信息、区域与局部信息、全局与区域信息进行提取和融合. 此外, 设计了一种层次特征融合方式来对CNN分支提取到的局部信息和划分窗口的Transformer提取到的区域信息进行特征融合. 大量的实验表明, 所提网络在轻量级SR领域实现了更好的结果. 例如, 在Manga109数据集的4倍放大实验中, 该网络的峰值信噪比(PSNR)相较于SwinIR提升了0. 51 dB.
Abstract:In recent years, with the development of deep learning techniques, convolutional neural network (CNN) and Transformers have made significant progress in image super-resolution. However, for the extraction of global features of an image, it is common to stack individual operators and repeat the computation to gradually expand the receptive field. To better utilize global information, this study proposes that local, regional, and global features should be explicitly modeled. Specifically, local information, regional-local information, and global-regional information of an image are extracted and fused hierarchically and progressively through channel attention-enhanced convolution, a dual-branch parallel architecture consisting of a window-based Transformer and CNN, and a dual-branch parallel architecture consisting of a standard Transformer and a window-based Transformer. In addition, a hierarchical feature fusion method is designed to fuse the local information extracted from the CNN branch and the regional information extracted from the window-based Transformer. Extensive experiments show that the proposed network achieves better results in lightweight SR. For example, in the 4× upscaling experiments on the Manga109 dataset, the peak signal-to-noise ratio (PSNR) of the proposed network is improved by 0.51 dB compared to SwinIR.
文章编号:     中图分类号:    文献标志码:
基金项目:
引用文本:
张豪,马冀,袁江.基于特征层次递进融合的轻量级图像超分辨率网络.计算机系统应用,,():1-10
ZHANG Hao,MA Ji,YUAN Jiang.Lightweight Image Super-resolution Network Based on Progressive Fusion of Hierarchical Feature.COMPUTER SYSTEMS APPLICATIONS,,():1-10