摘要
针对固定网络架构和深度网络层导致的信息无法完全表达复杂场景预测高质量图像、高计算成本及部署困难等问题,提出了一种具有宽网络结构的图像动态超分辨率网络(wide dynamic super-resolution network,W-SDNet).首先,设计了一个由移位卷积残差增强结构组成的残差增强块,以提高图像超分辨率的分层特征提取能力并减少计算成本.其次,引入一个宽增强模块通过其双分支的4层并行结构,在提取深度信息的同时利用动态网络的门机制选择性增强特征表达,同时通过边缘检测算子融合的注意力机制增强边缘细节的表现力.紧接着,采用组卷积和信道分割的细化块,以防止在广泛增强块中组件间的干扰.最后,通过一个构建块实现高质量图像的重建.实验结果表明,W-SDNet在5个公开测试数据集上放大4倍时的峰值信噪比(peak signal-to-noise ratio,PSNR)指标均优于现有主流算法,并且模型的参数量显著减少,证明了W-SDNet在超分辨率重建的复杂度、性能及恢复时间方面的优势.
To address the challenges posed by fixed network architectures and deep network layers,such as incomplete expression of complex scene predictions,high computational costs,and deployment difficulties,this study proposes a new network called wide structure dynamic super-resolution network(W-SDNet).Initially,a residual enhancement block,consisting of shift convolution residual structures,is designed to enhance the capability of extracting hierarchical features for image super-resolution and to reduce computational costs.Next,a wide enhancement module is introduced,employing a dual-branch four-layer parallel structure to extract deep information while using a dynamic network’s gating mechanism to selectively enhance feature expression.This module also utilizes an attention mechanism that integrates edge detection operators to improve the expressiveness of edge details.To prevent interference among components within the wide enhancement block,a refinement block utilizing group convolution and channel splitting is employed.Ultimately,highquality image reconstruction is achieved through a construction block.Experimental results show that W-SDNet outperforms the existing mainstream algorithms in peak signal-to-noise ratio(PSNR)metrics when zoomed in 4 times on five publicly available test datasets,and the number of parameters in the model is significantly reduced.The results demonstrate the advantages of W-SDNet in terms of complexity,performance,and recovery time of super-resolution reconstruction.
作者
沈学利
朱晓铭
金海波
SHEN Xue-Li;ZHU Xiao-Ming;JIN Hai-Bo(Software College,Liaoning Technical University,Huludao 125105,China)
出处
《计算机系统应用》
2024年第9期65-76,共12页
Computer Systems & Applications
基金
国家自然科学基金面上项目(62173171)。
关键词
图像超分辨率
移位卷积
动态网络
边缘检测
注意力机制
image super-resolution
shift convolution
dynamic network
edge detection
attention mechanism
