Deep Learning for Image Super-Resolution: A Survey

By Zhihao Wang, Jian Chen, Steven C. H. Hoi. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019

1,821 citations recorded by the source corpus.

Image Super-Resolution (SR) is an important class of image processing techniqueso enhance the resolution of images and videos in computer vision. Recent years have witnessed remarkable progress of image super-resolution using deep learning techniques. This article aims to provide a comprehensive survey on recent advances of image super-resolution using deep learning approaches. In general, we can roughly group the existing studies of SR techniques into three major categories: supervised SR, unsupervised SR, and domain-specific SR. In addition, we also cover some other important issues, such as publicly available benchmark datasets and performance evaluation metrics. Finally, we conclude this survey by highlighting several future directions and open issues which should be further addressed by the community in the future.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/155f27879f185f1ab04107c91c2ae7cf6a910a03

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

DATFuse: Infrared and Visible Image Fusion via Dual Attention Transformer (2023, positive): “Due to its powerful feature representation capability, deep learning (DL) has been successfully applied to computer vision tasks such as image super-resolution [48], image restoration [49], and person re-identiﬁcation [50], [51].”
Uformer: A General U-Shaped Transformer for Image Restoration (2021, background): “More CNN-based image restoration architectures can be found in the recent surveys [31,54,62] and the NTIRE Challenges [2].”
Lightweight Image Super-Resolution with Adaptive Weighted Learning Network (2019, methodology): “proposed a convolutional neural networks (CNN) based SR (SRCNN) algorithm that outperformed its previous work [1], various improved algorithms have been proposed for SISR with superior performance [2,4,5].”
DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis (2020, background): “The last few years have witnessed the great success of Generative Adversarial Networks (GANs) [8] for a variety of applications [4,27,48].”
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.”
Artificial intelligence in the creative industries: a review (2020, background): “arpness and textural detail, cannot simultaneously achieve low distortion loss (e.g. mean absolute error (MAE) or peak signal-to-noise-ratio (PSNR)). A comprehensive survey of image SR is provided in [260]. This observes that more complex networks generally produce better PSNR results and that most ”
MADNet: A Fast and Lightweight Network for Single-Image Super Resolution (2020, background): “Addressing SISR has proven to be useful in many practical cases, such as video streaming [44], [50]; remote sensing [16], [58]; and medical imaging [31], [45], [48].”
Exploiting Aliasing for Manga Restoration (2021, background): “This seems very similar to the formula adopted in superresolution [26], but the problem is crucially different due to the special nature of manga restoration.”
Efficient Image Super-Resolution Using Pixel Attention (2020, methodology): “Some of these modules have been utilized in SR and shows effectiveness [1,36].”
Learning Enriched Features for Fast Image Restoration and Enhancement (2022, methodology): “The data-driven SR approaches differ according to their architecture designs [55], [56], [57].”
SinSR: Diffusion-Based Image Super-Resolution in a Single Step (2023, background): “With the rise of deep learning, deep learning-based techniques gradually become the mainstream of the SR task [8, 45].”
Learning Enriched Features for Real Image Restoration and Enhancement (2020, methodology): “Here, we compute the PSNR and SSIM scores using the Y channel (in YCbCr color space), as it is a common practice in the SR literature [125,14,106,6].”