BROWSE

ITEM VIEW & DOWNLOAD

Unsupervised training of deep learning based image denoisers from undersampled measurements

Cited 0 times inthomson ciCited 0 times inthomson ci
Title
Unsupervised training of deep learning based image denoisers from undersampled measurements
Author
Zhussip, Magauiya
Advisor
Chun, Se Young
Issue Date
2019-08
Publisher
Graduate School of UNIST
Abstract
Compressive sensing is a method to recover the original image from undersampled measurements. In order to overcome the ill-posedness of this inverse problem, image priors are used such as sparsity, minimal total-variation, or self-similarity of images. Recently, deep learning based compressive image recovery methods have been proposed and have yielded state-of-the-art performances. They used data-driven approaches instead of hand-crafted image priors to regularize ill-posed inverse problems with undersampled data. Ironically, training deep neural networks (DNNs) for them requires “clean” ground truth images, but obtaining the best quality images from undersampled data requires well-trained DNNs. To resolve this dilemma, we propose novel methods based on two well-grounded theories: denoiser-approximate message passing (D-AMP) and Stein’s unbiased risk estimator (SURE). Our proposed methods, LDAMP SURE and LDAMP SURE-T, were able to train deep learning based image denoisers from undersampled measurements without ground truth images and without additional image priors and to recover images with state-of-the-art qualities from undersampled data. We evaluated our methods for various compressive sensing recovery problems with Gaussian random, coded diffraction pattern, and compressive sensing MRI (CS-MRI) measurement matrices. Our proposed methods yielded state-of-the-art performances for all cases without ground truth images. Our methods also yielded comparable performances to the approaches with ground truth data. Moreover, we have extended our methods to deal with a Gaussian noise in a measurement domain and further enhance reconstruction quality by developing an image refining method called LDAMP SURE-FT.
Description
Department of Electrical Engineering
URI
Go to Link
Appears in Collections:
EE_Theses_Master
Files in This Item:
Unsupervised training of deep learning based image denoisers from undersampled measurements.pdf Download

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show full item record

qrcode

  • mendeley

    citeulike

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

MENU