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

By Wenming Yang, Xuechen Zhang, Yapeng Tian, Wei Wang, Jing-Hao Xue, Qingmin Liao. IEEE transactions on multimedia, 2018

1,052 citations recorded by the source corpus.

Single image super-resolution (SISR) is a notoriously challenging ill-posed problem that aims to obtain a high-resolution output from one of its low-resolution 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.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/058976101d10f532ea0b1385bf639247c71e92f0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment (2020, methodology): “face restoration, most existing methods typically work in a “non-blind” fashion with specific degradation of prescribed type and intensity, leading to a variety of sub-tasks including super resolution[58][8][34][55], hallucination [47][29], denoising[1][60], deblurring[48][25][26]andcompressionartif”
Artificial intelligence in the creative industries: a review (2020, methodology): “hitecture [257]. The above techniques seek to learn implicit redundancy that is present in natural data to recover missing HR information from a single LR instance. For single image SR, the review in [259] suggests that methods such as EnhanceNet [97] and SRGAN [104], that achieve high subjective qu”
Intermediate Layer Optimization for Inverse Problems using Deep Generative Models (2021, background): “Finally, there is signiﬁcant prior work on deep learning meth-ods that do not rely on pre-trained generators, see e.g. (Lucas et al., 2018; Yu et al., 2019; Liu et al., 2019; Sun & Chen, 2020; Sun et al., 2020; Yang et al., 2019; Tian et al., 2020; Tripathi et al., 2018).”
Domain Fingerprints for No-Reference Image Quality Assessment (2019, background): “ual quality of a degraded image without the corresponding reference for comparison. It serves as a key component in low-level computer vision community. In practice, many tasks like image restoration [1], [2]and image generation [3] adopt full-reference SSIM and PSNR as metrics to evaluate the quali”
Toward Real-World Single Image Super-Resolution: A New Benchmark and a New Model (2019, background): “SISR has been an active research topic for decades [38, 57, 45, 47, 5] because of its high practical values in enhancing image details and textures.”
Learned Image Downscaling for Upscaling Using Content Adaptive Resampler (2019, methodology): “More reviews and discussion about single image SR using deep learning can be referred to [8].”
DeepEMhancer: a deep learning solution for cryo-EM volume post-processing (2020, neutral): “Particularly, our development, which follows a simple image super-resolution setup 18 , exploits the vast amount of structural information that is contained in the Electron Microscopy Data Bank (EMDB) database 19 in order to mimic the local sharpening effect of the LocScale algorithm.”
TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution (2018, background): “A recent survey about deep learning-based SISR methods is in [33].”
The 2018 PIRM Challenge on Perceptual Image Super-Resolution (2018, background): “Traditionally, neural networks for single image SR are trained with `1/`2 norm objectives [53, 47].”
Real-World Single Image Super-Resolution: A Brief Review (2021, methodology): “Considering that deep learning has been widely employed to address SR over the past few years, more recently Yang et al. [125], Wang et al. [126], and Liu et al. [127] review deep learning-based image/video SR methods.”
TTST: A Top-k Token Selective Transformer for Remote Sensing Image Super-Resolution (2024, background): “Subsequently, with the booming of deep learning [21], the deep-learning-based SR approaches have achieved significant performance [22], [23], [24].”
Cali-Sketch: Stroke Calibration and Completion for High-Quality Face Image Generation from Poorly-Drawn Sketches (2019, positive): “In recent years, Generative Adversarial Networks (GANs) [23] have been successfully applied in many computer vision tasks to improve realism of generated images, such as domain adaption [24], [25], [26], super-resolution [27], [28], [29], [30], [31], [32].”
2018 PIRM Challenge on Perceptual Image Super-resolution (2018, background): “Traditionally, neural networks for single image SR are trained with `1/`2 norm objectives [53, 47].”
Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception (2020, background): “Although SISR is relatively less studied in the underwater domain, a rich body of literature exists for terrestrial imagery [66].”
Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning (2022, background): “Following many works in super resolution [61], the low frequency target image is obtained by interpolating Ihr to a much lower resolution, rlow and then interpolating to the same resolution as the input image I .”