2020/01/21 by Seyed Mehdi Ayyoubzadeh, Xiaolin Wu, Ayyoubzadeh, Seyed Mehdi +1
Computer Science · Engineering · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image Processing Techniques and Applications #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2001.07766
openalex publication_date 2020/01/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Single Image Super-Resolution (SISR) task refers to learn a mapping from low-resolution images to the corresponding high-resolution ones. This task is known to be extremely difficult since it is an ill-posed problem. Recently, Convolutional Neural Networks (CNNs) have achieved state of the art performance on SISR. However, the images produced by CNNs do not contain fine details of the images. Generative Adversarial Networks (GANs) aim to solve this issue and recover sharp details. Nevertheless, GANs are notoriously difficult to train. Besides that, they generate artifacts in the high-resolution images. In this paper, we have proposed a method in which CNNs try to align images in different spaces rather than only the pixel space. Such a space is designed using convex optimization techniques. CNNs are encouraged to learn high-frequency components of the images as well as low-frequency components. We have shown that the proposed method can recover fine details of the images and it is stable in the training process.