Results 11 to 20 of about 216,992 (320)
Blind Super-Resolution Based on Interframe Information Compensation for Satellite Video
IEEE Journal of Selected Topics in Applied Earth Observations and Remote SensingSuper-resolution (SR) of satellite video has long been a critical research direction in the field of remote sensing video processing and analysis, and blind SR has attracted increasing attention in the face of satellite video with unknown degradation ...
Hongliang Chang +4 more
doaj +2 more sources
Taming Stable Diffusion for Computed Tomography Blind Super-Resolution
MedAGIHigh-resolution computed tomography (CT) imaging is essential for medical diagnosis but requires increased radiation exposure, creating a critical trade-off between image quality and patient safety. While deep learning methods have shown promise in CT super-resolution, they face challenges with complex degradations and limited medical training data ...
Li, Chunlei +5 more
openaire +3 more sources
Remote SensingMost existing deep learning-based super-resolution (SR) methods for remote sensing images rely on predefined degradation assumptions (e.g., bicubic downsampling).
Guanwen Li +3 more
doaj +2 more sources
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data [PDF]
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021 Though many attempts have been made in blind super-resolution to restore low-resolution images with unknown and complex degradations, they are still far from addressing general real-world degraded images.
Xintao Wang +3 more
semanticscholar +1 more source
Unsupervised Degradation Representation Learning for Blind Super-Resolution [PDF]
Computer Vision and Pattern Recognition, 2021 Most existing CNN-based super-resolution (SR) methods are developed based on an assumption that the degradation is fixed and known (e.g., bicubic downsampling).
Longguang Wang +6 more
semanticscholar +1 more source
Training ESRGAN with multi-scale attention U-Net discriminator [PDF]
Scientific ReportsIn this paper, we propose MSA-ESRGAN, a novel super-resolution model designed to enhance the perceptual quality of images. The key innovation of our approach lies in the integration of a multi-scale attention U-Net discriminator, which allows for more ...
Quan Chen, Hao Li, Gehao Lu
doaj +2 more sources
Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors [PDF]
ACM Multimedia, 2022 A key challenge of real-world image super-resolution (SR) is to recover the missing details in low-resolution (LR) images with complex unknown degradations (\eg, downsampling, noise and compression).
Chaofeng Chen +6 more
semanticscholar +1 more source
Lightweight Implicit Blur Kernel Estimation Network for Blind Image Super-Resolution
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 +1 more source
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
Blind Super-Resolution via Projected Gradient Descent
2022 IEEE International Symposium on Information Theory (ISIT), 2022 Blind super-resolution can be cast as low rank matrix recovery problem by exploiting the inherent simplicity of the signal. In this paper, we develop a simple yet efficient nonconvex method for this problem based on the low rank structure of the vectorized Hankel matrix associated with the target matrix.
Mao, Sihan, Chen, Jinchi
openaire +2 more sources