Block matching super-resolution parallel GPU implementation for computational imaging

2017 ◽  
Vol 63 (4) ◽  
pp. 368-376
Author(s):  
E. Marenzi ◽  
E. Torti ◽  
F. Leporati ◽  
E. Quevedo ◽  
G. M. Callicò
Keyword(s):  
Super Resolution ◽  
Computational Imaging ◽  
Block Matching ◽  
Gpu Implementation

Analysis of fast block matching motion estimation algorithms for video super-resolution systems

2008 ◽  
Vol 54 (3) ◽  
pp. 1430-1438 ◽  
Author(s):  
Gustavo Callico ◽  
Sebastian Lopez ◽  
Oliver Sosa ◽  
Jose Lopez ◽  
Roberto Sarmiento
Keyword(s):  
Motion Estimation ◽  
Super Resolution ◽  
Block Matching ◽  
Estimation Algorithms

scholarly journals NON-LINEAR MULTI-FRAME IMAGE DENOISING USING WEIGHTED NUCLEAR NORM MINIMIZATION

2021 ◽  
Vol XLIV-2/W1-2021 ◽  
pp. 167-170
Author(s):  
A. V. Nasonov ◽  
O. S. Volodina ◽  
A. S. Krylov
Keyword(s):  
Image Denoising ◽  
Super Resolution ◽  
Low Noise ◽  
Block Matching ◽  
Norm Minimization ◽  
Noise Image ◽  
Multiple Input ◽  
Noticeable Improvement ◽  
Repeated Structure ◽  
Weighted Nuclear Norm Minimization

Abstract. We address the problem of constructing single low noise image from a sequence of multiple noisy images. We use the approach based on finding and averaging similar blocks in the image and extend it to multiple images. Unlike traditional multi-frame super-resolution algorithms, the block-matching approach does not require computationally expensive motion estimation for multi-frame image denoising. In this work, we use an algorithm based on weighted nuclear minimization for image denoising. The evaluation of the algorithm shows noticeable improvement of image quality when using multiple input images instead of single one. The improvement is the most noticeable in the areas with complex non-repeated structure.

Sign in / Sign up

Export Citation Format

Share Document