Results 231 to 240 of about 137,048 (270)

Deep Blind Hyperspectral Image Super-Resolution

IEEE Transactions on Neural Networks and Learning Systems, 2021
The production of a high spatial resolution (HR) hyperspectral image (HSI) through the fusion of a low spatial resolution (LR) HSI with an HR multispectral image (MSI) has underpinned much of the recent progress in HSI super-resolution. The premise of these signs of progress is that both the degeneration from the HR HSI to LR HSI in the spatial domain ...
Lei Zhang 0054, Jiangtao Nie, Wei Wei 0008, Yong Li, Yanning Zhang 0001   +4 more
openaire   +2 more sources

Fast and Robust ADMM for Blind Super-Resolution

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
Though the blind super-resolution problem is nonconvex in nature, recent advance shows the feasibility of a convex formulation which gives the unique recovery guarantee. However, the convexification procedure is coupled with a huge computational cost and is therefore of great interests to investigate fast algorithms.
Yifan Ran, Wei Dai 0001
openaire   +1 more source

Nonparametric Blind Super-resolution

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   +1 more source

Non-stationary blind super-resolution

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016
In this paper, we propose a new framework for parameter estimation of complex exponentials from their modulations with unknown waveforms via convex programming. Our model generalizes the recently developed blind sparse spike deconvolution framework by Y. Chi [1] to the non-stationary scenario and encompasses a wide spectrum of applications.
Dehui Yang, Gongguo Tang, Michael B. Wakin   +2 more
openaire   +1 more source

Dynamic learnable degradation for blind super-resolution

Expert Systems with Applications
Ling Xu, Qingguo Xiao, Qiaochuan Chen, Guangyao Li   +3 more
openaire   +3 more sources

Patch based blind image super resolution

Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005
In this paper, a novel method for learning based image super resolution (SR) is presented. The basic idea is to bridge the gap between a set of low resolution (LR) images and the corresponding high resolution (HR) image using both the SR reconstruction constraint and a patch based image synthesis constraint in a general probabilistic framework. We show
Qiang Wang 0023, Xiaoou Tang, Harry Shum
openaire   +1 more source

Blind Super-resolution of Faces for Surveillance

2021
Super-resolution (SR) refers to a class of techniques that derive a high resolution image from its low resolution (LR) counterpart. A vast amount of literature exists on SR spanning both multi and single image approaches.
T. M. Nimisha, A. N. Rajagopalan
openaire   +1 more source

KernelNet: A Blind Super-Resolution Kernel Estimation Network

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021
Recently developed deep neural network methods have achieved remarkable performance in the Super Resolution problem when applied to Low Resolution (LR) images that are obtained from High Resolution (HR) images with ideal and predefined downsampling processing, i.e., convolution with a known blurring kernel that is followed by subsampling (e.g., Bicubic)
Mehmet Yamac, Baran Ataman, Aakif Nawaz
openaire   +1 more source

Blind super-resolution of sparse spike signals

2015 49th Asilomar Conference on Signals, Systems and Computers, 2015
In many applications, the observations can be modeled as a linear combination of a small number of scaled and shifted copies of a bandlimited point spread function, either determined by the nature or designed by the users. Examples include neural spike trains, returns in radar and sonar, images in astronomy and single-molecule microscopy, etc. It is of
openaire   +1 more source

MAP Based Blind Super-Resolution

2012 International Conference on Industrial Control and Electronics Engineering, 2012
Super-resolution is the process of obtaining a high resolution image from multiple low resolution images. In most of the super-resolution algorithms, the blur parameter of a LR-image model always have to be manually set as a default value, this is not a good solution.
Liu Gang, Hu Zhenlong
openaire   +1 more source