Cascaded Degradation-Aware Blind Super-Resolution [PDF]
Sensors, 2023 Image super-resolution (SR) usually synthesizes degraded low-resolution images with a predefined degradation model for training. Existing SR methods inevitably perform poorly when the true degradation does not follow the predefined degradation ...
Ding Zhang +3 more
doaj +5 more sources
Blur Kernel Estimation and Non-Blind Super-Resolution for Power Equipment Infrared Images by Compressed Sensing and Adaptive Regularization [PDF]
Sensors, 2021 Infrared sensing technology is more and more widely used in the construction of power Internet of Things. However, due to cost constraints, it is difficult to achieve the large-scale installation of high-precision infrared sensors.
Hongshan Zhao +2 more
doaj +3 more sources
Lightweight Implicit Blur Kernel Estimation Network for Blind Image Super-Resolution [PDF]
Information, 2023 Blind image super-resolution (Blind-SR) is the process of leveraging a low-resolution (LR) image, with unknown degradation, to generate its high-resolution (HR) version.
Asif Hussain Khan +2 more
doaj +5 more sources
Research on Blind Super-Resolution Technology for Infrared Images of Power Equipment Based on Compressed Sensing Theory [PDF]
Sensors, 2021 Infrared images of power equipment play an important role in power equipment status monitoring and fault identification. Aiming to resolve the problems of low resolution and insufficient clarity in the application of infrared images, we propose a blind ...
Yan Wang +3 more
doaj +2 more sources
High-speed blind structured illumination microscopy via unsupervised algorithm unrolling [PDF]
Nature CommunicationsBlind structured illumination microscopy (blind-SIM) is a valuable tool for achieving super-resolution without the need for known illumination patterns.
Zachary Burns +4 more
doaj +2 more sources
AI, 2023 Despite several solutions and experiments have been conducted recently addressing image super-resolution (SR), boosted by deep learning (DL), they do not usually design evaluations with high scaling factors.
Valdivino Alexandre de Santiago Júnior
doaj +2 more sources
Super-Resolution-Assisted Farmland Boundary Extraction from Medium-Resolution Satellite Image: A Real-ESRGAN and YOLO Segmentation Framework [PDF]
SensorsThis study addresses the issue of insufficient spatial resolution in remote sensing images for farmland boundary identification in precision agriculture.
Junyao Yu +8 more
doaj +2 more sources
Deep Learning-Based Single-Image Super-Resolution: A Comprehensive Review
IEEE Access, 2023 High-fidelity information, such as 4K quality videos and photographs, is increasing as high-speed internet access becomes more widespread and less expensive.
Karansingh Chauhan +7 more
doaj +1 more source
Pixel-Level Kernel Estimation for Blind Super-Resolution
IEEE Access, 2021 Throughout the past several years, deep learning-based models have achieved success in super-resolution (SR). The majority of these works assume that low-resolution (LR) images are ‘uniformly’ degraded from their corresponding high ...
Jaihyun Lew, Euiyeon Kim, Jae-Pil Heo
doaj +1 more source
Medical image blind super‐resolution based on improved degradation process
IET Image Processing, 2023 Clinical diagnosis has high requirements for the resolution of medical images, but most existing medical images super‐ resolution (SR) methods are performed under a known or specific degradation kernel.
Dangguo Shao +4 more
doaj +1 more source