Laser & Optoelectronics Progress, Volume. 58, Issue 4, 0410013(2021)
Image Super-Resolution Reconstruction Method Based on Self-Attention Deep Network
It is difficult to fully recover the image details using the existing image super-resolution reconstruction methods. Furthermore, the reconstructed images lack a hierarchy. To address these problems, an image super-resolution reconstruction method based on self-attention deep networks is proposed herein. This method, which is based on deep neural networks, reconstructs a high-resolution image using the features extracted from a corresponding low-resolution image. It nonlinearly maps the features of a low-resolution image to those of a high-resolution image. In the process of nonlinear mapping, the self-attention mechanism is utilized to obtain the dependence among all the pixels in the images, and the global features of the images are used to reconstruct the corresponding high-resolution image, which promotes image hierarchy. During the deep neural network training, a loss function comprising a pixel-wise loss and a perceptual loss is utilized to improve the image-detail reconstruction ability of the neural network. Experiments on three open datasets show that the proposed method outperforms the existing methods in terms of image-detail reconstruction. Furthermore, the visual impression of the reconstructed image is better than that of the images reconstructed using other existing methods.
Get Citation
Copy Citation Text
Zihan Chen, Haobo Wu, Haodong Pei, Rong Chen, Jiaxin Hu, Hengtong Shi. Image Super-Resolution Reconstruction Method Based on Self-Attention Deep Network[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0410013
Category: Image Processing
Received: Jun. 30, 2020
Accepted: Aug. 7, 2020
Published Online: Feb. 25, 2021
The Author Email: Wu Haobo (haobow@126.com), Pei Haodong (haobow@126.com)