Image restoration (IR) from noisy, blurred or/and incomplete observed measurement is one of the important tasks in image processing community. Image prior is of utmost importance for recovering a high quality image. I...
详细信息
Image restoration (IR) from noisy, blurred or/and incomplete observed measurement is one of the important tasks in image processing community. Image prior is of utmost importance for recovering a high quality image. In this paper, we present a two-stage convolutionalsparse prior model for efficient image restoration. The multi-view features prior is first obtained by convolving the image with the Fields-of Experts (FoE) filters and then the resulting multi-view features are represented by convolutional sparse coding (CSC) prior. By taking advantage of the convolutional filters, the proposed two-stage model inherits the strengths of multi-view features and CSC priors. The assembled multi-view features contain high frequency, redundancy, and large range of feature orientations, which are favor to be represented by CSC and consequently for better image recovery. Augmented Lagrangian and alternating direction method of multipliers are employed to decouple the nonlinear optimization problem in order to iteratively approach the optimum solution. The results of various experiments on image deblurring and compressed sensing magnetic resonance imaging (CS-MRI) reconstruction consistently demonstrate that the proposed algorithm efficiently recovers image and presents advantages over the current leading restoration approaches. (C) 2017 Elsevier Inc. All rights reserved.
Denoising is often addressed via sparsecoding with respect to an overcomplete dictionary. There are two main approaches when the dictionary is composed of translates of an orthonormal basis. The first, traditionally ...
详细信息
Denoising is often addressed via sparsecoding with respect to an overcomplete dictionary. There are two main approaches when the dictionary is composed of translates of an orthonormal basis. The first, traditionally employed by techniques such as wavelet cycle spinning, separately seeks sparsity w.r.t. each translate of the orthonormal basis, solving multiple partial optimizations and obtaining a collection of sparse approximations of the noise-free image, which are aggregated together to obtain a final estimate. The second approach, recently employed by convolutionalsparse representations, instead seeks sparsity over the entire dictionary via a global optimization. It is tempting to view the former approach as providing a suboptimal solution of the latter. In this letter, we analyze whether global sparsity is a desirable property, and under what conditions the global optimization provides a better solution to the denoising problem. In particular, our experimental analysis shows that the two approaches attain comparable performance in case of natural images and global optimization outperforms the simpler aggregation of partial estimates only when the image admits an extremely sparse representation. We explain this phenomenon by separately studying the bias and variance of these solutions, and by noting that the variance of the global solution increases very rapidly as the original signal becomes less and less sparse.
While convolutionalsparse representations enjoy a number of useful properties, they have received limited attention for image reconstruction problems. The present paper compares the performance of block-based and con...
详细信息
ISBN:
(纸本)9781538646595
While convolutionalsparse representations enjoy a number of useful properties, they have received limited attention for image reconstruction problems. The present paper compares the performance of block-based and convolutionalsparse representations in the removal of Gaussian white noise. The usual formulation of the convolutional sparse coding problem is slightly inferior to the block-based representations in this problem, but the performance of the convolutional form can be boosted beyond that of the block-based form by the inclusion of suitable penalties on the gradients of the coefficient maps.
Synthesis learning and analysis learning, with sparsecoding (SC) and Markov random fields (MRFs) as two representative types of models, are two complementary tools to describe the image manifolds. SC has strengths in...
详细信息
ISBN:
(纸本)9781509021758
Synthesis learning and analysis learning, with sparsecoding (SC) and Markov random fields (MRFs) as two representative types of models, are two complementary tools to describe the image manifolds. SC has strengths in representing the regular features/explicit visual manifolds while its effectiveness depends on the training dataset. While MRFs have great potentials to characterize the stochastic textures/implicit visual manifolds but at the cost of high training complexity. In this paper, by means of the convolutional operator, a unified synthesis and analysis deconvolutional network (SADN) is presented. It not only requires the generative coding coefficients to be sparse, but also enforces the convolution between the filter and trained images to be sparse. The proposed model incorporates the strengths of both SC and MRFs, which enables it to represent general images with both generative and discriminative abilities. The resulting minimization is tackled by the combination of alternating optimization and Iterative Re-weighted Least Square (IRLS). Experiments conducted on compressed sensing (CS) application show its great potentials both quantitatively and qualitatively.
Objects in fine-grained categories always share a high degree of shape similarity, making both "localizing discriminative parts" and "learning appearance descriptors" extremely difficult. We propos...
详细信息
ISBN:
(纸本)9781467399616
Objects in fine-grained categories always share a high degree of shape similarity, making both "localizing discriminative parts" and "learning appearance descriptors" extremely difficult. We propose a framework to leverage 2D+3D cues to handle above two challenges. Towards the goal of image alignment to localize discriminative parts, traditional methods rely on either manual part annotation or image segmentation. Instead, our framework leverages each image's 3D camera pose estimation to align images;Towards the goal of "learning appearance descriptors" confined with small training data and memory/computation cost, we propose an unsupervised convolutional sparse coding (CSC) + manifold learning that significantly reduces model complexity, but still successfully produces highly diverse feature filters like deep neural network. Our experimental results attest the advocated framework's accuracy is comparable to a deep network, demonstrating its great potential on mobile devices.
Standard sparse representations, applied independently to a set of overlapping image blocks, are a very effective approach to a wide variety of image reconstruction problems. convolutionalsparse representations, whic...
详细信息
ISBN:
(纸本)9781509019298
Standard sparse representations, applied independently to a set of overlapping image blocks, are a very effective approach to a wide variety of image reconstruction problems. convolutionalsparse representations, which provide a single-valued representation optimised over an entire image, provide an alternative form of sparse representation that has recently started to attract interest for image reconstruction problems. The present paper provides some insight into the suitability of the convolutional form for this type of application by comparing its performance as an image model with that of the standard model in an impulse noise restoration problem.
convolutionalsparse representations differ from the standard form in representing the signal to be decomposed as the sum of a set of convolutions with dictionary filters instead of a linear combination of dictionary ...
详细信息
ISBN:
(纸本)9781467399616
convolutionalsparse representations differ from the standard form in representing the signal to be decomposed as the sum of a set of convolutions with dictionary filters instead of a linear combination of dictionary vectors. The advantage of the convolutional form is that it provides a single-valued representation optimised over an entire signal. The substantial computational cost of the convolutional sparse coding and dictionary learning problems has recently been shown to be greatly reduced by solving in the frequency domain, but the periodic boundary conditions imposed by this approach have the potential to create boundary artifacts. The present paper compares different approaches to avoiding these effects in both sparsecoding and dictionary learning.
Objects in fine-grained categories always share a high degree of shape similarity, making both "localizing discriminative parts" and "learning appearance descriptors" extremely difficult. We propos...
详细信息
ISBN:
(纸本)9781467399623
Objects in fine-grained categories always share a high degree of shape similarity, making both "localizing discriminative parts" and "learning appearance descriptors" extremely difficult. We propose a framework to leverage 2D+3D cues to handle above two challenges. Towards the goal of image alignment to localize discriminative parts, traditional methods rely on either manual part annotation or image segmentation. Instead, our framework leverages each image's 3D camera pose estimation to align images;Towards the goal of "learning appearance descriptors" confined with small training data and memory/computation cost, we propose an unsupervised convolutional sparse coding (CSC) + manifold learning that significantly reduces model complexity, but still successfully produces highly diverse feature filters like deep neural network. Our experimental results attest the advocated framework's accuracy is comparable to a deep network, demonstrating its great potential on mobile devices.
Learning filters to produce sparse image representations in terms of overcomplete dictionaries has emerged as a powerful way to create image features for many different purposes. Unfortunately, these filters are usual...
详细信息
Learning filters to produce sparse image representations in terms of overcomplete dictionaries has emerged as a powerful way to create image features for many different purposes. Unfortunately, these filters are usually both numerous and non-separable, making their use computationally expensive. In this paper, we show that such filters can be computed as linear combinations of a smaller number of separable ones, thus greatly reducing the computational complexity at no cost in terms of performance. This makes filter learning approaches practical even for large images or 3D volumes, and we show that we significantly outperform state-of-the-art methods on the curvilinear structure extraction task, in terms of both accuracy and speed. Moreover, our approach is general and can be used on generic convolutional filter banks to reduce the complexity of the feature extraction step.
暂无评论