Super-resolution: a comprehensive survey

K Nasrollahi, TB Moeslund - Machine vision and applications, 2014‏ - Springer
Super-resolution, the process of obtaining one or more high-resolution images from one or
more low-resolution observations, has been a very attractive research topic over the last two …

A review on Single Image Super Resolution techniques using generative adversarial network

K Singla, R Pandey, U Ghanekar - Optik, 2022‏ - Elsevier
Abstract Single Image Super Resolution (SISR) is a process to obtain a high pixel density
and refined details from a low resolution (LR) image to get upscaled and sharper high …

TTST: A Top-k Token Selective Transformer for Remote Sensing Image Super-Resolution

Y **ao, Q Yuan, K Jiang, J He, CW Lin… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Transformer-based method has demonstrated promising performance in image super-
resolution tasks, due to its long-range and global aggregation capability. However, the …

Details or artifacts: A locally discriminative learning approach to realistic image super-resolution

J Liang, H Zeng, L Zhang - … of the IEEE/CVF conference on …, 2022‏ - openaccess.thecvf.com
Single image super-resolution (SISR) with generative adversarial networks (GAN) has
recently attracted increasing attention due to its potentials to generate rich details. However …

Structure-preserving super resolution with gradient guidance

C Ma, Y Rao, Y Cheng, C Chen… - Proceedings of the …, 2020‏ - openaccess.thecvf.com
Structures matter in single image super resolution (SISR). Recent studies benefiting from
generative adversarial network (GAN) have promoted the development of SISR by …

Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network

W Shi, J Caballero, F Huszár, J Totz… - Proceedings of the …, 2016‏ - cv-foundation.org
Recently, several models based on deep neural networks have achieved great success in
terms of both reconstruction accuracy and computational performance for single image …

Efficient and degradation-adaptive network for real-world image super-resolution

J Liang, H Zeng, L Zhang - European Conference on Computer Vision, 2022‏ - Springer
Efficient and effective real-world image super-resolution (Real-ISR) is a challenging task
due to the unknown complex degradation of real-world images and the limited computation …

Single image super-resolution from transformed self-exemplars

JB Huang, A Singh, N Ahuja - … of the IEEE conference on computer …, 2015‏ - cv-foundation.org
Self-similarity based super-resolution (SR) algorithms are able to produce visually pleasing
results without extensive training on external databases. Such algorithms exploit the …

Learning a no-reference quality metric for single-image super-resolution

C Ma, CY Yang, X Yang, MH Yang - Computer Vision and Image …, 2017‏ - Elsevier
Numerous single-image super-resolution algorithms have been proposed in the literature,
but few studies address the problem of performance evaluation based on visual perception …

A novel fuzzy hierarchical fusion attention convolution neural network for medical image super-resolution reconstruction

C Wang, X Lv, M Shao, Y Qian, Y Zhang - Information Sciences, 2023‏ - Elsevier
The clarity of medical images is crucial for doctors to identify and diagnose different
diseases. High-resolution images have more detailed information and clearer content than …