李浪, 陶洋. 一种轻量图像超分辨率重建算法[J]. 微电子学与计算机, 2021, 38(11): 45-52. DOI: 10.19304/J.ISSN1000-7180.2021.0188
引用本文: 李浪, 陶洋. 一种轻量图像超分辨率重建算法[J]. 微电子学与计算机, 2021, 38(11): 45-52. DOI: 10.19304/J.ISSN1000-7180.2021.0188
LI Lang, TAO Yang. A light weight image super-resolution algorithm[J]. Microelectronics & Computer, 2021, 38(11): 45-52. DOI: 10.19304/J.ISSN1000-7180.2021.0188
Citation: LI Lang, TAO Yang. A light weight image super-resolution algorithm[J]. Microelectronics & Computer, 2021, 38(11): 45-52. DOI: 10.19304/J.ISSN1000-7180.2021.0188

一种轻量图像超分辨率重建算法

A light weight image super-resolution algorithm

  • 摘要: 目前大多数图像超分辨率重建算法都是通过堆叠卷积神经网络的深度和宽度来提升算法的重建能力.虽然这些算法能够在一定程度上提升重建效果,但是算法复杂度高.为了改善这一问题,提出一种基于注意力机制和特征融合的轻量超分辨率重建算法.首先利用像素注意力机制,对不同的特征的像素进行加权;随后利用轻量级通道注意力机制模块设计多级特征融合模块, 并通过全局残差连接进行全局的特征融合;最后对提取到的特征进行亚像素卷积上采样.将本算法在Set5、Set14、BSD100以及Urban100这四个图像超分辨率重建领域常用公开数据集上进行实验.实验结果表明,与对比算法相比,在图像评价指标上,具备更高的峰值信噪比和结构相似性;在视觉效果上,和对比算法的重建图像相比,本算法重建的图像具备更丰富的细节;同时与对比算法相比,所提算法具备最少的参数量.

     

    Abstract: At present, most image super-resolution reconstruction algorithms improve the reconstruction ability of the algorithm by increasing the depth or width of the convolutional neural network. Although these algorithms can improve the reconstruction effect to a certain extent, the algorithm complexity is high. In order to improve this problem, a lightweight super-resolution reconstruction algorithm based on attention mechanism and feature fusion is proposed. Based on the pixel attention mechanism, pixels with different characteristics are weighted. Subsequently, a multi-level feature fusion module is designed based on the lightweight channel attention mechanism module, and further uses the global residual connection to perform global feature fusion. Finally, sub-pixel convolution up-sampling is performed on the extracted features. The algorithm is tested on four commonly used public data sets in the field of image super-resolution reconstruction, Set5, Set14, BSD100, and Urban100. The experimental results show that compared with others algorithms, in terms of image evaluation indicators, it has a higher peak signal-to-noise ratio and structural similarity. In terms of visual effects, compared with the reconstructed image of the contrast algorithm, the image reconstructed by this algorithm has richer details.At the same time, compared with the comparison algorithm, the proposedalgorithm has the least amount of parameters.

     

/

返回文章
返回