TY - GEN
T1 - Image Restoration by Deep Projected GSURE
AU - Abu-Hussein, Shady
AU - Tirer, Tom
AU - Chun, Se Young
AU - Eldar, Yonina C.
AU - Giryes, Raja
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution. In recent years, solutions that are based on deep Convolutional Neural Networks (CNNs) have shown great promise. Yet, most of these techniques, which train CNNs using external data, are restricted to the observation models that have been used in the training phase. A recent alternative that does not have this drawback relies on learning the target image using internal learning. One such prominent example is the Deep Image Prior (DIP) technique that trains a network directly on the input image with the least-squares loss. In this paper, we propose a new image restoration framework that is based on minimizing a loss function that includes a "projected-version"of the Generalized Stein Unbiased Risk Estimator (GSURE) and parameterization of the latent image by a CNN. We propose two ways to use our framework. In the first one, where no explicit prior is used, we show that the proposed approach outperforms other internal learning methods, such as DIP. In the second one, we show that our GSURE-based loss leads to improved performance when used within a plug-and-play priors scheme.
AB - Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution. In recent years, solutions that are based on deep Convolutional Neural Networks (CNNs) have shown great promise. Yet, most of these techniques, which train CNNs using external data, are restricted to the observation models that have been used in the training phase. A recent alternative that does not have this drawback relies on learning the target image using internal learning. One such prominent example is the Deep Image Prior (DIP) technique that trains a network directly on the input image with the least-squares loss. In this paper, we propose a new image restoration framework that is based on minimizing a loss function that includes a "projected-version"of the Generalized Stein Unbiased Risk Estimator (GSURE) and parameterization of the latent image by a CNN. We propose two ways to use our framework. In the first one, where no explicit prior is used, we show that the proposed approach outperforms other internal learning methods, such as DIP. In the second one, we show that our GSURE-based loss leads to improved performance when used within a plug-and-play priors scheme.
KW - Deep Learning
KW - Image Processing
KW - Image Processing
KW - Image Restoration Computational Photography
KW - Image and Video Synthesis
UR - http://www.scopus.com/inward/record.url?scp=85126120724&partnerID=8YFLogxK
U2 - 10.1109/WACV51458.2022.00017
DO - 10.1109/WACV51458.2022.00017
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85126120724
T3 - Proceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022
SP - 91
EP - 100
BT - Proceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 22nd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022
Y2 - 4 January 2022 through 8 January 2022
ER -