Deep Learning for Single Image Super-Resolution: A Brief Review

Abstract

Single image super-resolution (SISR) is a notoriously challenging ill-posed problem that aims to obtain a highresolution (HR) output from one of its low-resolution (LR) versions. Recently, powerful deep learning algorithms have been applied to SISR and have achieved state-of-the-art performance. In this survey, we review representative deep learning-based SISR methods and group them into two categories according to their contributions to two essential aspects of SISR: the exploration of efficient neural network architectures for SISR and the development of effective optimization objectives for deep SISR learning. For each category, a baseline is first established, and several critical limitations of the baseline are summarized. Then, representative works on overcoming these limitations are presented based on their original content, as well as our critical exposition and analyses, and relevant comparisons are conducted from a variety of perspectives. Finally, we conclude this review with some current challenges and future trends in SISR that leverage deep learning algorithms.

Image Super Resolution via Bilinear Pooling: Application to Confocal Endomicroscopy

“…Our results show a moderate quantitative increase in PSNR score and a consid- erable increase in qualitative performance -this is similar to previous works in single image super resolution [20]. Fig.…”

Widefield light sheet microscopy using an Airy beam combined with deep-learning super-resolution

“…In microscopy, deep-learning has been typically used to surpass the diffraction limit to achieve super-resolution microscopy [28]. However, in a broader context of image processing, deep-learning has been applied to a class of problems termed single-image super-resolution [29], the goal of which is to enhance resolution in poor sampling regimes. In this case, and as demonstrated in this paper, deep-learning may be used to effectively resolve sub-Nyquist-sampled features without necessarily breaching the fundamental diffraction limit.…”

ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network

“…The main approaches to SISR can be divided into three distinct categories: interpolation-based methods, reconstructionbased methods and learning-based methods [9]. Approaches based on deep learning have further surpassed the two former methods as well as simple learning-based methods.…”