Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration

Chen, Yunjin; Pock, Thomas

doi:10.1109/tpami.2016.2596743

Cited by 1,165 publications

(911 citation statements)

References 59 publications

Supporting

Mentioning

910

Contrasting

Unclassified

Order By: Relevance

“…Only few works such employ this property directly [10], but also results for learned shrinkage functions suggest its usefulness [4]. The corresponding concept of backward diffusion has also shown to be successful [11,12,13].…”

Section: Introductionmentioning

confidence: 99%

Learning a Generic Adaptive Wavelet Shrinkage Function for Denoising

Alt

Weickert

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

The rise of machine learning in image processing has created a gap between trainable data-driven and classical modeldriven approaches: While learning-based models often show superior performance, classical ones are often more transparent. To reduce this gap, we introduce a generic wavelet shrinkage function for denoising which is adaptive to both the wavelet scales as well as the noise standard deviation. It is inferred from trained results of a tightly parametrised function which is inherited from nonlinear diffusion. Our proposed shrinkage function is smooth and compact while only using two parameters. In contrast to many existing shrinkage functions, it is able to enhance image structures by amplifying wavelet coefficients. Experiments show that it outperforms classical shrinkage functions by a significant margin.

show abstract

Section: Introductionmentioning

confidence: 99%

Learning a Generic Adaptive Wavelet Shrinkage Function for Denoising

Alt

Weickert

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…It was unfit to perform well on pictures with obscure noise levels. Additionally, it requires the output which is expected by the network during training [6]. In 2011, Deng transformed the inpainting task to the graph-labeling task using graph Laplace method.…”

Section: Related Workmentioning

confidence: 99%

Semantic Image Completion and Enhancement using Deep Learning

Chandak¹,

Saxena²,

Pattanaik³

et al. 2019

2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)

View full text Add to dashboard Cite

In real life applications, certain images utilized are corrupted in which the image pixels are damaged or missing, which increases the complexity of computer vision tasks. In this paper, a deep learning architecture is proposed to deal with image completion and enhancement. Generative Adversarial Networks (GAN), has been turned out to be helpful in picture completion tasks. Therefore, in GANs, Wasserstein GAN architecture is used for image completion which creates the coarse patches to filling the missing region in the distorted picture, and the enhancement network will additionally refine the resultant pictures utilizing residual learning procedures and hence give better complete pictures for computer vision applications. Experimental outcomes show that the proposed approach improves the Peak Signal to Noise ratio and Structural Similarity Index values by 2.45% and 4% respectively, when compared to the recently reported data.

show abstract

“…Note that this scheme can be interpreted as a discretized reaction–diffusion equation (cf. [2]) or as the time-discrete projected gradient flow [8] of a time-dependent variational energy. In this work, we propose to use the following coupled variational energy:The first term couples the reconstructed image and the segmentation mask by means of convolution operations and parameterized nonlinear functions.…”

Section: A Coupled Variational Networkmentioning

confidence: 99%

Joint reconstruction and classification of tumor cells and cell interactions in melanoma tissue sections with synthesized training data

et al. 2019

Self Cite

View full text Add to dashboard Cite

PurposeCancers are almost always diagnosed by morphologic features in tissue sections. In this context, machine learning tools provide new opportunities to describe tumor immune cell interactions within the tumor microenvironment and thus provide phenotypic information that might be predictive for the response to immunotherapy.MethodsWe develop a machine learning approach using variational networks for joint image denoising and classification of tissue sections for melanoma, which is an established model tumor for immuno-oncology research. The manual annotation of real training data would require substantial user interaction of experienced pathologists for each single training image, and the training of larger networks would rely on a very large number of such data sets with ground truth annotation. To overcome this bottleneck, we synthesize training data together with a proper tissue structure classification. To this end, a stochastic data generation process is used to mimic cell morphology, cell distribution and tissue architecture in the tumor microenvironment. Particular components of this tool are random placement and rotation of a large number of patches for presegmented cell nuclei, a stochastic fast marching approach to mimic the geometry of cells and texture generation based on a color covariance analysis of real data. Here, the generated training data reflect a large range of interaction patterns.ResultsIn several applications to histological tissue sections, we analyze the efficiency and accuracy of the proposed approach. As a result, depending on the scenario considered, almost all cells and nuclei which ought to be detected are actually marked as classified and hardly any misclassifications occur.ConclusionsThe proposed method allows for a computer-aided screening of histological tissue sections utilizing variational networks with a particular emphasis on tumor immune cell interactions and on the robust cell nuclei classification.

show abstract

Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration

Cited by 1,165 publications

References 59 publications

Learning a Generic Adaptive Wavelet Shrinkage Function for Denoising

Learning a Generic Adaptive Wavelet Shrinkage Function for Denoising

Semantic Image Completion and Enhancement using Deep Learning

Joint reconstruction and classification of tumor cells and cell interactions in melanoma tissue sections with synthesized training data

Contact Info

Product

Resources

About