A review of image super-resolution approaches based on deep learning and applications in remote sensing

X Wang, J Yi, J Guo, Y Song, J Lyu, J Xu, W Yan… - Remote Sensing, 2022‏ - mdpi.com
At present, with the advance of satellite image processing technology, remote sensing
images are becoming more widely used in real scenes. However, due to the limitations of …

Spherical pseudo-cylindrical representation for omnidirectional image super-resolution

Q Cai, M Li, D Ren, J Lyu, H Zheng, J Dong… - Proceedings of the …, 2024‏ - ojs.aaai.org
Omnidirectional images have attracted significant attention in recent years due to the rapid
development of virtual reality technologies. Equirectangular projection (ERP), a naive form …

Multicontrast mri super-resolution via transformer-empowered multiscale contextual matching and aggregation

J Lyu, G Li, C Wang, Q Cai, Q Dou… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Magnetic resonance imaging (MRI) possesses the unique versatility to acquire images
under a diverse array of distinct tissue contrasts, which makes multicontrast super-resolution …

HIPA: hierarchical patch transformer for single image super resolution

Q Cai, Y Qian, J Li, J Lyu, YH Yang… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Transformer-based architectures start to emerge in single image super resolution (SISR)
and have achieved promising performance. However, most existing vision Transformer …

Bridging component learning with degradation modelling for blind image super-resolution

Y Wu, F Li, H Bai, W Lin, R Cong… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Convolutional Neural Network (CNN)-based image super-resolution (SR) has exhibited
impressive success on known degraded low-resolution (LR) images. However, this type of …

MHGAN: A multi-headed generative adversarial network for underwater sonar image super-resolution

Z Ma, S Li, J Ding, B Zou - IEEE Transactions on Geoscience …, 2023‏ - ieeexplore.ieee.org
Super-resolution (SR) is a technique for recovering image details based on available
information, avoiding image quality degradation by increasing an image's resolution …

Single image super-resolution based on trainable feature matching attention network

Q Chen, Q Shao - Pattern Recognition, 2024‏ - Elsevier
Abstract Convolutional Neural Networks (CNNs) have been widely employed for image
Super-Resolution (SR) in recent years. Various techniques enhance SR performance by …

Sea-net: Structure-enhanced attention network for limited-angle cbct reconstruction of clinical projection data

D Hu, Y Zhang, W Li, W Zhang, K Reddy… - IEEE Transactions …, 2023‏ - ieeexplore.ieee.org
This work aims to improve limited-angle (LA) cone-beam computed tomography (CBCT) by
develo** deep learning (DL) methods for real clinical CBCT projection data, which is the …

Perception-distortion balanced super-resolution: A multi-objective optimization perspective

L Sun, J Liang, S Liu, H Yong… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
High perceptual quality and low distortion degree are two important goals in image
restoration tasks such as super-resolution (SR). Most of the existing SR methods aim to …

A feature reuse framework with texture-adaptive aggregation for reference-based super-resolution

X Mei, Y Yang, M Li, C Huang, K Zhang… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Reference-based super-resolution (RefSR) has gained considerable success in the field of
super-resolution with the addition of high-resolution reference images to reconstruct low …