Skip links to main content
Logo of Geometric Image Processing Laboratory,
Computer Science Department Home
Technion Home Page

Projects Last Projects

Deep Learning of Compressed Sensing Operators with Structural Similarity Loss

Yochai Zur

Supervised by Amir Adler

Abstract

Compressed sensing (CS) is a signal processing framework for efficiently reconstructing a signal from a small number of measurements, obtained by linear projections of the signal. In this paper we present an end-to-end deep learning approach for CS, in which a fully-connected network performs both the linear sensing and non-linear reconstruction stages. During the training phase, the sensing matrix and the non-linear reconstruction operator are jointly optimized using Structural similarity index (SSIM) as loss rather than the standard Mean Squared Error (MSE) loss. We compare the proposed approach with state-of-the-art in terms of reconstruction quality under both losses, i.e. SSIM score and MSE score.

Source code available here: https://github.com/yochaiz/SSIM

Papers

Please, see project papers.

Pictures
Project Deep Learning of Compressed Sensing Operators with Structural Similarity Loss Picture 1
Project Deep Learning of Compressed Sensing Operators with Structural Similarity Loss Picture 2
Project Deep Learning of Compressed Sensing Operators with Structural Similarity Loss Picture 3
Project Deep Learning of Compressed Sensing Operators with Structural Similarity Loss Picture 4
Project Report

Please, see project report.

Final Presentation

Please, see final presentation.

Copyright © 2016 by Geometric Image Processing Lab. All rights reserved.