Results 11 to 20 of about 2,688,199 (290)
Nonparametric Blind Super-resolution [PDF]
2013 IEEE International Conference on Computer Vision, 2013 Super resolution (SR) algorithms typically assume that the blur kernel is known (either the Point Spread Function 'PSF' of the camera, or some default low-pass filter, e.g. a Gaussian). However, the performance of SR methods significantly deteriorates when the assumed blur kernel deviates from the true one.
Tomer Michaeli, Michal Irani
openaire +3 more sources
Multi-Frame Blind Super-Resolution Based on Joint Motion Estimation and Blur Kernel Estimation
Applied Sciences, 2022 Multi-frame super-resolution makes up for the deficiency of sensor hardware and significantly improves image resolution by using the information of inter-frame and intra-frame images.
Shanshan Liu +2 more
doaj +2 more sources
Simultaneous super-resolution and blind deconvolution [PDF]
Journal of Physics: Conference Series, 2008 This work has been partially supported by the projects TEC 2004-00834, TEC2005-24739-E, TEC2005-24046-E, PI040765, 2004CZ0009 CSIC-Academy of Sciences of the Czech Republic, No. 202/05/0242 of the Grant Agency of the Czech Republic and No. 1M0572 (Research Center DAR) of the Czech Ministry of Education.
Sroubek, F. +2 more
openaire +3 more sources
A Progressive Decoupled Network for Blind Image Super-Resolution
IEEE AccessBlind super-resolution (Blind SR) has become a popular research topic in computer vision in super-resolution, which aims to enhance low-resolution (LR) images with unknown or partially known degradation blur kernels.
Laigan Luo, Benshun Yi, Chao Zhu
doaj +3 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 +3 more sources
Geocarto InternationalDespite natural image super-resolution (SR) methods have achieved great success, super-resolution methods for hyperspectral image (HSI) with rich spectral features are still a very challenging task.
Lijing Bu +3 more
doaj +2 more sources
Blind Super-Resolution with Deep Convolutional Neural Networks
, 2016 Example-based methods have demonstrated their ability to perform well for Single Image Super-Resolution (SR). While very efficient when a single image formation model (non-blind) is assumed for the low-resolution (LR) observations, they fail when a LR image is not compliant with this model, producing noticeable artifacts on the final SR image.
Clément Peyrard +2 more
openaire +2 more sources
Super-Resolution Blind Channel Modeling [PDF]
2011 IEEE International Conference on Communications (ICC), 2011 In this work, we propose a super-resolution blind channel modeling algorithm to characterize wide-band channels comprised of disjoint frequency subbands. Since sounding signals are not available over the frequency guard bands separating adjacent subbands, conventional channel modeling methods suffer from poor performance in modeling the channel ...
Man-On Pun +3 more
openaire +2 more sources
Deep Blind Video Super-resolution
CoRR, 2020 Existing video super-resolution (SR) algorithms usually assume that the blur kernels in the degradation process are known and do not model the blur kernels in the restoration. However, this assumption does not hold for video SR and usually leads to over-smoothed super-resolved images.
Jinshan Pan +3 more
openaire +2 more sources
Deep Blind Super-Resolution for Satellite Video
IEEE Transactions on Geoscience and Remote Sensing, 2023 Recent efforts have witnessed remarkable progress in Satellite Video Super-Resolution (SVSR). However, most SVSR methods usually assume the degradation is fixed and known, e.g., bicubic downsampling, which makes them vulnerable in real-world scenes with multiple and unknown degradations.
Yi Xiao 0003 +3 more
openaire +4 more sources