Deep Convolutional Autoencoders for Deblurring and Denoising Low-Resolution Images

Michael Fernando Mendez Jimenez; Omar DeGuchy; Roummel Marcia

Summary

2020

Session Number:D02

Session:

Number:D02-1

Deep Convolutional Autoencoders for Deblurring and Denoising Low-Resolution Images

Michael Fernando Mendez Jimenez, Omar DeGuchy, Roummel Marcia,

pp.549-553

Publication Date:2020/10/18

Online ISSN:2188-5079

DOI:10.34385/proc.65.D02-1

PDF download

Summary:

In this paper, we implement machine learning
methods to recover higher-dimensional signals from lower-
dimensional, noisy, and blurry measurements. In particular,
rather than utilizing optimization-based reconstruction methods,
we use fully-connected multilayer perceptron (MLP) architectures and convolutional neural networks (CNN). In addition, we
consider two different loss functions based on mean squared
error and a Huber potential to train our models. Numerical
experiments on the Street View House Numbers dataset show that
while fully-connected MLPs are faster to train, reconstructions
using CNNs are much more accurate.