Results 261 to 270 of about 216,992 (320)
Some of the next articles are maybe not open access.
KernFusNet: Implicit Kernel Modulation and Fusion for Blind Super-Resolution
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)Convolutional neural network-based super-resolution (SR) methods have achieved significant success on ideal, predefined downsampling (bicubic) kernels. However, these algorithms struggle with unknown degradations in real-world data, which often follow a ...
Nancy Mehta +3 more
semanticscholar +1 more source
IEEE Transactions on Instrumentation and Measurement
Existing degradation kernel-based image super-resolution (SR) algorithms have achieved favorable performance in blind SR measurement. This addresses the limitation where bicubic kernel-based SR methods suffer performance degradation when the input image ...
Haoran Yang +3 more
semanticscholar +1 more source
Existing degradation kernel-based image super-resolution (SR) algorithms have achieved favorable performance in blind SR measurement. This addresses the limitation where bicubic kernel-based SR methods suffer performance degradation when the input image ...
Haoran Yang +3 more
semanticscholar +1 more source
Kernel-aware network with dual diffusion model for MRI blind super resolution
Measurement science and technologyMagnetic resonance imaging (MRI) offers abundant and rich information to help doctors quickly diagnose patients’ diseases. Due to patients’ movement, the obtained MRI is blurry, which may have a great influence on the accuracy of clinical diagnosis.
Xiao-qiang Zhao +2 more
semanticscholar +1 more source
Real-world blind super-resolution using stereoscopic feature and coupled optimization
Neural NetworksBlind super-resolution is typically decomposed into degradation estimation and image restoration to mitigate the ill-condition. Most existing methods employ two independent models to address these two sub-problems separately.
Guangyi Ji, Xiao Hu
semanticscholar +1 more source
BSRNet: Blind Super-Resolution of Low-Dose CT Images Based on Adaptive Routing
International Conference on Computer Science, Environment, Ecoinformatics, and EducationConventional super-resolution (SR) methods for computed tomography (CT) typically rely on a fixed degradation model, such as downsampling and noise. However, the actual degradation process is more complex, making it difficult to accurately recover fine ...
Menglei Gao, Peng Wu
semanticscholar +1 more source
Robust Non-Stationary Blind Super-Resolution with Corrupted Measurements via Convex Demixing
International Conference on Digital Signal ProcessingThis paper addresses the problem of robust non-stationary blind super-resolution in the presence of gross corruptions in the measurement data. By employing a subspace model for the modulated unknown waveforms and utilizing a lifting trick, we reformulate
Dehui Yang
semanticscholar +1 more source
Blind super-resolution of turbulence-degraded imagery
Conference Record of Thirty-Second Asilomar Conference on Signals, Systems and Computers (Cat. No.98CH36284), 2002The blind restoration problem has seen significant progress with the demonstration of estimation theoretic methods by T. Schulz (1993). In this paper we present further extension to the problem of blind super-resolution. The problem of interest in this paper is the super-resolution of imagery acquired through a turbulent atmosphere, where super ...
D. Sheppard, B.R. Hunt
openaire +1 more source
Blind Super-Resolution of Remote Sensing Images for Various Degradation Scenarios
2025 5th International Conference on Neural Networks, Information and Communication Engineering (NNICE)The spatial resolution of satellite images is significantly degraded due to limitations in optical imaging hardware and atmospheric conditions, restricting the broader application of remote sensing technology.
Bili Lin +3 more
semanticscholar +1 more source
Riemannian Gradient Descent Method for Joint Blind Super-Resolution and Demixing
International Conference on Signal Processing SystemsIntegrated Sensing and Communication (ISAC) has emerged as a promising technology for next-generation wireless networks. In this work, we tackle an ill-posed parameter estimation problem within ISAC, formulating it as a joint blind super-resolution and ...
Zeyu Xiang +6 more
semanticscholar +1 more source
Blind Super Resolution with Reference Images and Implicit Degradation Representation
Asian Conference on Computer VisionPrevious studies in blind super-resolution (BSR) have primarily concentrated on estimating degradation kernels directly from low-resolution (LR) inputs to enhance super-resolution.
Huu-Phu Do +5 more
semanticscholar +1 more source