Image Restoration with Deep Generative Models

Yeh, Raymond A.; Lim, Teck Yian; Chen, Chen; Schwing, Alexander G.; Hasegawa‐Johnson, Mark; Minh, N.

doi:10.1109/icassp.2018.8462317

Cited by 22 publications

(18 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We hypothesized that an intact edge could enhance the overall system performance due to its intrinsic high frequency information and its ability to constrain contrast matching. The performance of our proposed edge-guided image restoration network supports this hypothesis by demonstrating higher PSNR and SSIM than the widely used context encoder, which was initially designed for generating the contents of an arbitrary image region conditioned on its surroundings [27], [38], [56].…”

Section: Discussionsupporting

confidence: 59%

MRI Restoration Using Edge-Guided Adversarial Learning

Chai

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) images acquired as multislice two-dimensional (2D) images present challenges when reformatted in orthogonal planes due to sparser sampling in the throughplane direction. Restoring the ''missing'' through-plane slices, or regions of an MRI image damaged by acquisition artifacts can be modeled as an image imputation task. In this work, we consider the damaged image data or missing through-plane slices as image masks and proposed an edge-guided generative adversarial network to restore brain MRI images. Inspired by the procedure of image inpainting, our proposed method decouples image repair into two stages: edge connection and contrast completion, both of which used general adversarial networks (GAN). We trained and tested on a dataset from the Human Connectome Project to test the application of our method for thick slice imputation, while we tested the artifact correction on clinical data and simulated datasets. Our Edge-Guided GAN had superior PSNR, SSIM, conspicuity and signal texture compared to traditional imputation tools, the Context Encoder and the Densely Connected Super Resolution Network with GAN (DCSRN-GAN). The proposed network may improve utilization of clinical 2D scans for 3D atlas generation and big-data comparative studies of brain morphometry.

show abstract

Section: Discussionsupporting

confidence: 59%

MRI Restoration Using Edge-Guided Adversarial Learning

Chai

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In the second version, we assume that the blurring coefficients and the selected channel are unknown, implying that we simultaneously estimate them and restore the original image. For the deblurring, we solve (8) under the constraint that the filter coefficients sum to one.…”

Section: Methodsmentioning

confidence: 99%

“…For the colorization, we notice that the channel decomposition is a linear transformation implemented with three matrices T R , T G , T B as in (10). The fact that the unknown parameter is now discrete does not pose any special difficulty in the optimization in (8), which must be modified as followŝ…”

Section: Methodsmentioning

confidence: 99%

“…Because of this fact, several approaches attempted to solve inverse problems using generative priors for the original data. Early efforts were using the generative model partially (only the generator function) [6,7,8,9]. Only recently [10,11] we see techniques that employ the complete model (generator and input density) improving the performance of the corresponding methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Single Image Restoration with Generative Priors

Basioti

Moustakides

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Generative models can be used, as an alternative to conventional probability densities, to capture the statistical behavior of complicated datasets. Unlike probability densities with which the generation of realizations may become a challenging task, generative models have an inherent ability to easily produce realizations, which, in the case of natural images can be extremely realistic. In many image restoration problems, such as deblurring, colorization, inpainting, super-resolution, etc., probability densities are used as priors, one may therefore wonder whether we can, instead, adopt generative models. Indeed such methods have appeared in the literature, but they require exact knowledge of the transformations responsible for the data distortion and involve regularizer terms with weights that require adjustment. Our approach, by combining maximum a-posteriori probability with maximum likelihood estimation, can successfully restore images in both blind and non-blind modes without the need to fine-tune any regularization parameters. Simulations on deblurring, colorization, and image separation problems with exact knowledge of the transformation demonstrate improved image quality, reduced computational cost compared to existing methods. Comparable results are also enjoyed when the distortion models contain unknown parameters.

show abstract

“…For improving denoising speed, optimization method cooperated CNN was a good tool to rapidly find optimal solution in image denoising [35,51]. For example, a GAN with maximum a posteriori (MAP) was used to estimate the noise and deal with other tasks, such as image inpainting and super-resolution [210]. An experience-based greedy and transfer learning strategies with CNN can accelerate genetic algorithm to obtain a clean image [122].…”

Section: The Combination Of Optimization Methods and Cnn/nn For Awni ...mentioning

confidence: 99%

Deep Learning on Image Denoising: An overview

Tian

Zhang

Zheng³

et al. 2019

Preprint

View full text Add to dashboard Cite

Deep learning techniques have obtained much attention in image denoising. However, deep learning methods of different types deal with the noise have enormous differences. Specifically, discriminative learning based on deep learning can well address the Gaussian noise. Optimization model methods based on deep learning have good effect on estimating of the real noise. So far, there are little related researches to summarize different deep learning techniques for image denoising. In this paper, we make such a comparative study of different deep techniques in image denoising. We first classify the (1) deep convolutional neural networks (CNNs) for additive white noisy images, (2) deep CNNs for real noisy images, (3) deep CNNs for blind denoising and (4) deep CNNs for hybrid noisy images, which is the combination of noisy, blurred and low-resolution images. Then, we analyze the motivations and principles of deep learning methods of different types. Next, we compare and verify the state-of-the-art methods on public denoising datasets in terms of quantitative and qualitative analysis. Finally, we point out some potential challenges and directions of future research.

show abstract

Image Restoration with Deep Generative Models

Cited by 22 publications

References 8 publications

MRI Restoration Using Edge-Guided Adversarial Learning

MRI Restoration Using Edge-Guided Adversarial Learning

Single Image Restoration with Generative Priors

Deep Learning on Image Denoising: An overview

Contact Info

Product

Resources

About