scholarly journals Uniform Motion Blur in Poissonian Noise: Blur/Noise Tradeoff

2011 ◽  
Vol 20 (2) ◽  
pp. 592-598 ◽  
Author(s):  
Giacomo Boracchi ◽  
Alessandro Foi
2015 ◽  
Vol 24 (7) ◽  
pp. 2067-2082 ◽  
Author(s):  
Abhijith Punnappurath ◽  
Ambasamudram Narayanan Rajagopalan ◽  
Sima Taheri ◽  
Rama Chellappa ◽  
Guna Seetharaman

2021 ◽  
Vol 55 ◽  
pp. 44-53
Author(s):  
Misak Shoyan ◽  
◽  
Robert Hakobyan ◽  
Mekhak Shoyan ◽  

In this paper, we present deep learning-based blind image deblurring methods for estimating and removing a non-uniform motion blur from a single blurry image. We propose two fully convolutional neural networks (CNN) for solving the problem. The networks are trained end-to-end to reconstruct the latent sharp image directly from the given single blurry image without estimating and making any assumptions on the blur kernel, its uniformity, and noise. We demonstrate the performance of the proposed models and show that our approaches can effectively estimate and remove complex non-uniform motion blur from a single blurry image.


Sign in / Sign up

Export Citation Format

Share Document