Results 21 to 30 of about 137,048 (270)
Unfolding the Alternating Optimization for Blind Super Resolution
CoRR, 2020 Conference on Neural Information Processing Systems (NeurIPS ...
Zhengxiong Luo 0001 +4 more
openaire +3 more sources
Sensors, 2022 To date, the best-performing blind super-resolution (SR) techniques follow one of two paradigms: (A) train standard SR networks on synthetic low-resolution–high-resolution (LR–HR) pairs or (B) predict the degradations of an LR image and then use these to
Matthew Aquilina +5 more
doaj +1 more source
Contrastive learning for a single historical painting’s blind super-resolution
Visual Informatics, 2021 Most of the existing blind super-resolution(SR) methods explicitly estimate the kernel in pixel space, which usually has a large deviation and results in poor SR performance.
Hongzhen Shi +4 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.
Sihan Mao, Jinchi Chen
openaire +2 more sources
DynaVSR: Dynamic Adaptive Blind Video Super-Resolution [PDF]
2021 IEEE Winter Conference on Applications of Computer Vision (WACV), 2021 Most conventional supervised super-resolution (SR) algorithms assume that low-resolution (LR) data is obtained by downscaling high-resolution (HR) data with a fixed known kernel, but such an assumption often does not hold in real scenarios. Some recent blind SR algorithms have been proposed to estimate different downscaling kernels for each input LR ...
Suyoung Lee +2 more
openaire +2 more sources
Blind assessment of localisation microscope image resolution [PDF]
, 2012 Background This paper analyses the resolution achieved in localisation microscopy experiments. The resolution is an essential metric for the correct interpretation of super-resolution images, but it varies between specimens due to different localisation ...
Erdelyi, M +5 more
core +2 more sources
Blind Super-Resolution With Iterative Kernel Correction [PDF]
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019 Deep learning based methods have dominated super-resolution (SR) field due to their remarkable performance in terms of effectiveness and efficiency. Most of these methods assume that the blur kernel during downsampling is predefined/known (e.g., bicubic).
Jinjin Gu +3 more
openaire +2 more sources
IET Image Processing, 2021 The current super‐resolution (SR) deep network is mainly applied to the common image and pays little attention to the image with noise. The remote sensing image contains much noise, so that the SR reconstruction effect is not satisfactory.
Xin Yang +3 more
doaj +1 more source
Blind fluorescence structured illumination microscopy: A new reconstruction strategy [PDF]
, 2016 In this communication, a fast reconstruction algorithm is proposed for fluorescence \textit{blind} structured illumination microscopy (SIM) under the sample positivity constraint.
Allain, M. +6 more
core +4 more sources
Unsupervised Blur Kernel Estimation and Correction for Blind Super-Resolution
IEEE Access, 2022 Blind super-resolution (blind-SR) is an important task in the field of computer vision and has various applications in real-world. Blur kernel estimation is the main element of blind-SR along with the adaptive SR networks and a more accurately estimated ...
Youngsoo Kim +3 more
doaj +1 more source