Multi-scale Weighted Nuclear Norm Image Restoration

Noam, Yair; Michaeli, Tomer

doi:10.1109/cvpr.2018.00334

Cited by 80 publications

(46 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This has contributed to the enthusiasm, but also hype, surrounding Deep Learning. classical denoising algorithms in computer vision research use sparse coding techniques 35 , low-rank decomposition 36 , or image self-similarity 37,38 . The lesson learned over time is that to effectively denoise an image, it is better to look beyond small patches of pixels and gather information across multiple image regions and ideally learn from a large sets of images.…”

Section: Deep Learning For Image Reconstructionmentioning

confidence: 99%

Applications, Promises, and Pitfalls of Deep Learning for Fluorescence Image Reconstruction

Belthangady¹,

Royer²

2019

Preprint

View full text Add to dashboard Cite

Deep Learning is a recent and important addition to the computational toolbox available for image reconstruction in fluorescence microscopy. We review state-of-the-art applications such as image restoration, super-resolution, and light-field imaging, and discuss how the latest Deep Learning research can be applied to other image reconstruction tasks such as structured illumination, spectral deconvolution, and sample stabilisation. Despite its successes, Deep Learning also poses significant challenges, has often misunderstood capabilities, and overlooked limits. We will address key questions, such as: What are the challenges in obtaining training data? Can we discover structures not present in the training data? And, what is the danger of inferring unsubstantiated image details?

show abstract

Section: Deep Learning For Image Reconstructionmentioning

confidence: 99%

Applications, Promises, and Pitfalls of Deep Learning for Fluorescence Image Reconstruction

Belthangady¹,

Royer²

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…The Richardson-Lucy (RL) [22] and Wiener [23] deconvolutions are simple and effective methods but suffer from oversmoothed edges and ringing artifacts. Model optimization methods rely on image prior that is mainly used to characterize local smoothness (e.g., total variation (TV) norm [24,25], hyper-Laplacian (HL) prior [26,27]) and nonlocal self-similarity (e.g., iterative decoupled deblurring-block matching and 3D filtering (IDD-BM3D) [28], nonlocally centralized sparse representation (NCSR) [29], multi scale-weighted nuclear norm minimization (MS-WNNM) [30]) of images. However, optimization is often time consuming, and the solution can reach a local minimum for image prior-based regularization, which may not be sufficiently strong [31].…”

Section: Deconvolution Modelingmentioning

confidence: 99%

Blind Deblurring of Saturated Images Based on Optimization and Deep Learning for Dynamic Visual Inspection on the Assembly Line

Wang

Liu

2019

Symmetry

View full text Add to dashboard Cite

Image deblurring can improve visual quality and mitigates motion blur for dynamic visual inspection. We propose a method to deblur saturated images for dynamic visual inspection by applying blur kernel estimation and deconvolution modeling. The blur kernel is estimated in a transform domain, whereas the deconvolution model is decoupled into deblurring and denoising stages via variable splitting. Deblurring predicts the mask specifying saturated pixels, which are then discarded, and denoising is learned via the fast and flexible denoising network (FFDNet) convolutional neural network (CNN) at a wide range of noise levels. Hence, the proposed deconvolution model provides the benefits of both model optimization and deep learning. Experiments demonstrate that the proposed method suitably restores visual quality and outperforms existing approaches with good score improvements.

show abstract

“…Fan et al [26] propose an MSI denoising model based on nonlocal multitask sparse learning to fully exploit the nonlocal self-similarity of the MSI on the spatial domain. Low-rank minimization is another strategy to exploit the underlying low-rank matrix from its degraded observation [8], where weighted nuclear norm minimization (WNNM) [9] problem uses the F-norm to measure the difference between observed data matrix y and latent data matrix x, which can be formulated as min…”

Section: Traditional Algorithmsmentioning

confidence: 99%

“…To address this problem, over the last decades, numerous contributions for image restoration are addressed from diverse points of view. These algorithms can be concluded in to neighbor embedding methods [3][4][5], sparsity-based methods [6,7], and low-rank minimization [8,9]. Some representative algorithms are illustrated in Section 2.1.…”

Section: Introductionmentioning

confidence: 99%

Deep Memory Connected Neural Network for Optical Remote Sensing Image Restoration

Wang

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

The spatial resolution and clarity of remote sensing images are crucial for many applications such as target detection and image classification. In the last several decades, tremendous image restoration tasks have shown great success in ordinary images. However, since remote sensing images are more complex and more blurry than ordinary images, most of the existing methods are not good enough for remote sensing image restoration. To address such problem, we propose a novel method named deep memory connected network (DMCN) based on the convolutional neural network to reconstruct high-quality images. We build local and global memory connections to combine image detail with global information. To further reduce parameters and ease time consumption, we propose Downsampling Units, shrinking the spatial size of feature maps. We verify its capability on two representative applications, Gaussian image denoising and single image super-resolution (SR). DMCN is tested on three remote sensing datasets with various spatial resolution. Experimental results indicate that our method yields promising improvements and better visual performance over the current state-of-the-art. The PSNR and SSIM improvements over the second best method are up to 0.3 dB.

show abstract

Multi-scale Weighted Nuclear Norm Image Restoration

Cited by 80 publications

References 38 publications

Applications, Promises, and Pitfalls of Deep Learning for Fluorescence Image Reconstruction

Applications, Promises, and Pitfalls of Deep Learning for Fluorescence Image Reconstruction

Blind Deblurring of Saturated Images Based on Optimization and Deep Learning for Dynamic Visual Inspection on the Assembly Line

Deep Memory Connected Neural Network for Optical Remote Sensing Image Restoration

Contact Info

Product

Resources

About