[IPOL announce] new article: An Analysis of Multi-stage Progressive Image Restoration Network (MPRNet)

[announcements about the IPOL journal]

A new article is available in IPOL: https://www.ipol.im/pub/art/2023/446/


Boshra Rajaei, Sara Rajaei, and Hossein Damavandi,
An Analysis of Multi-stage Progressive Image Restoration Network (MPRNet),
Image Processing On Line, 13 (2023), pp. 140–152.
https://doi.org/10.5201/ipol.2023.446

Abstract
Multi-stage progressive image restoration network (MPRNet) is a 
three-stage CNN (convolutional neural network) for image restoration. 
MPRNet has been shown to provide high performance gains on several 
datasets for a range of image restoration problems including image 
denoising, deblurring, and deraining. The network is interesting because 
it manages to remove the three kinds of artifacts with a single 
architecture. Here, we provide an overview of the network and study its 
performance and computational complexity in comparison with other 
state-of-the-art methods.