Related papers: Image Restoration by Deep Projected GSURE

Image Restoration by Deep Projected GSURE

URL: http://arxiv.org/abs/2102.02485v1
Date: Thu, 4 Feb 2021 08:52:46 GMT
Title: Image Restoration by Deep Projected GSURE
Authors: Shady Abu-Hussein, Tom Tirer, Se Young Chun, Yonina C. Eldar, and Raja Giryes
Abstract summary: Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution. We propose a new image restoration framework that is based on minimizing a loss function that includes a "projected-version" of the Generalized SteinUnbiased Risk Estimator (GSURE) and parameterization of the latent image by a CNN.
Score: 115.57142046076164
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: 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 a 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 SteinUnbiased Risk Estimator (GSURE) and parameterization of the latent image by a CNN. We demonstrate 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.

Related papers

Chasing Better Deep Image Priors between Over- and Under-parameterization [63.8954152220162]
We study a novel "lottery image prior" (LIP) by exploiting DNN inherent sparsity. LIPworks significantly outperform deep decoders under comparably compact model sizes. We also extend LIP to compressive sensing image reconstruction, where a pre-trained GAN generator is used as the prior.
arXiv Detail & Related papers (2024-10-31T17:49:44Z)
Unsupervised Deep Learning-based Pansharpening with Jointly-Enhanced Spectral and Spatial Fidelity [4.425982186154401]
We propose a new deep learning-based pansharpening model that fully exploits the potential of this approach. The proposed model features a novel loss function that jointly promotes the spectral and spatial quality of the pansharpened data. Experiments on a large variety of test images, performed in challenging scenarios, demonstrate that the proposed method compares favorably with the state of the art.
arXiv Detail & Related papers (2023-07-26T17:25:28Z)
Variational Deep Image Restoration [20.195082841065947]
This paper presents a new variational inference framework for image restoration and a convolutional neural network (CNN) structure that can solve the restoration problems described by the proposed framework. Specifically, our method delivers state-of-the-art performance on Gaussian denoising, real-world noise reduction, blind image super-resolution, and JPEG compression artifacts reduction.
arXiv Detail & Related papers (2022-07-03T16:32:15Z)
Learning Discriminative Shrinkage Deep Networks for Image Deconvolution [122.79108159874426]
We propose an effective non-blind deconvolution approach by learning discriminative shrinkage functions to implicitly model these terms. Experimental results show that the proposed method performs favorably against the state-of-the-art ones in terms of efficiency and accuracy.
arXiv Detail & Related papers (2021-11-27T12:12:57Z)
Blind Image Restoration with Flow Based Priors [19.190289348734215]
In a blind setting with unknown degradations, a good prior remains crucial. We propose using normalizing flows to model the distribution of the target content and to use this as a prior in a maximum a posteriori (MAP) formulation. To the best of our knowledge, this is the first work that explores normalizing flows as prior in image enhancement problems.
arXiv Detail & Related papers (2020-09-09T21:40:11Z)
Deep Variational Network Toward Blind Image Restoration [60.45350399661175]
Blind image restoration is a common yet challenging problem in computer vision. We propose a novel blind image restoration method, aiming to integrate both the advantages of them. Experiments on two typical blind IR tasks, namely image denoising and super-resolution, demonstrate that the proposed method achieves superior performance over current state-of-the-arts.
arXiv Detail & Related papers (2020-08-25T03:30:53Z)
The Power of Triply Complementary Priors for Image Compressive Sensing [89.14144796591685]
We propose a joint low-rank deep (LRD) image model, which contains a pair of complementaryly trip priors. We then propose a novel hybrid plug-and-play framework based on the LRD model for image CS. To make the optimization tractable, a simple yet effective algorithm is proposed to solve the proposed H-based image CS problem.
arXiv Detail & Related papers (2020-05-16T08:17:44Z)
BP-DIP: A Backprojection based Deep Image Prior [49.375539602228415]
We propose two image restoration approaches: (i) Deep Image Prior (DIP), which trains a convolutional neural network (CNN) from scratch in test time using the degraded image; and (ii) a backprojection (BP) fidelity term, which is an alternative to the standard least squares loss that is usually used in previous DIP works. We demonstrate the performance of the proposed method, termed BP-DIP, on the deblurring task and show its advantages over the plain DIP, with both higher PSNR values and better inference run-time.
arXiv Detail & Related papers (2020-03-11T17:09:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.