基于并联卷积与残差网络的图像超分辨率重建

现有的图像超分辨率重建算法可以改善图像整体视觉效果或者提升重建图像的客观评价值，然而对图像感知效果和客观评价值的均衡提升效果不佳，且重建图像缺乏高频信息，导致纹理模糊。针对上述问题，提出了一种基于并联卷积与残差网络的图像超分辨率重建算法。首先，以并联结构为整体框架，在并联结构上采用不同卷积组合来丰富特征信息，并加入跳跃连接来进一步丰富特征信息并融合输出，从而提取更多的高频信息。其次，引入自适应残差网络以补充信息并优化网络性能。最后，采用感知损失来提升恢复后图像的整体质量。实验结果表明，相较于超分辨率卷积神经网络（SRCNN）、深度超分辨率重建网络（VDSR）和超分辨率生成对抗网络（SRGAN）等算法，所提算法在重建图像上有更好的表现，其放大效果图的细节纹理更清晰。在客观评价上，所提算法在4倍重建时的峰值信噪比（PSNR）和结构相似性（SSIM）相较于SRGAN分别平均提升了0.25 dB和0.019。

Image super-resolution reconstruction based on parallel convolution and residual network

The existing image super-resolution reconstruction algorithms can improve the overall visual effect of the image or promote the objective evaluation value of the reconstructed image， but have poor balanced improvement effect of image perception effect and objective evaluation value， and the reconstructed images lack high-frequency information， resulting in texture blur. Aiming at the above problems， an image super-resolution reconstruction algorithm based on parallel convolution and residual network was proposed. Firstly， taking the parallel structure as the overall framework， different convolution combinations were used on the parallel structure to enrich the feature information， and the jump connection was added to further enrich the feature information and fuse the output to extract more high-frequency information. Then， an adaptive residual network was introduced to supplement information and optimize network performance. Finally， perceptual loss was used to improve the overall quality of the restored image. Experimental results show that， compared with the algorithms such as Super-Resolution Convolutional Neural Network （SRCNN）， Very Deep convolutional network for Super-Resolution （VDSR） and Super-Resolution Generative Adversarial Network （SRGAN）， the proposed algorithm has better performance in image reconstruction and has clearer detail texture of the enlarged effect image. In the objective evaluation， the Peak Signal-To-Noise Ratio （PSNR） and Structural SIMilarity （SSIM） of the proposed algorithm in \times \mathrm{4} reconstruction are improved by 0.25 dB and 0.019 averagely and respectively compared with those of SRGAN.