This paper proposes a novel approach to regularize the ill-posed blind image deconvolution (blind image deblurring) problem using deep generative networks. We employ two separate deep generative models - one trained to produce sharp images while the other trained to generate blur kernels from lower dimensional parameters. To deblur, we propose an alternating gradient descent scheme operating in the latent lower-dimensional space of each of the pretrained generative models. Our experiments show excellent deblurring results even under large blurs and heavy noise. To improve the performance on rich image datasets not well learned by the generative networks, we present a modification of the proposed scheme that governs the deblurring process under both generative and classical priors.
Due to image blurring image deconvolution is often used for studying biological structures in fluorescence microscopy. Fluorescence microscopy image volumes inherently suffer from intensity inhomogeneity, blur, and are corrupted by various types of noise which exacerbate image quality at deeper tissue depth. Therefore, quantitative analysis of fluorescence microscopy in deeper tissue still remains a challenge. This paper presents a three dimensional blind image deconvolution method for fluorescence microscopy using 3-way spatially constrained cycle-consistent adversarial networks. The restored volumes of the proposed deconvolution method and other well-known deconvolution methods, denoising methods, and an inhomogeneity correction method are visually and numerically evaluated. Experimental results indicate that the proposed method can restore and improve the quality of blurred and noisy deep depth microscopy image visually and quantitatively.
In blind image deconvolution, priors are often leveraged to constrain the solution space, so as to alleviate the under-determinacy. Priors which are trained separately from the task of deconvolution tend to be instable, or ineffective. We propose the Golf Optimizer, a novel but simple form of network that learns deep priors from data with better propagation behavior. Like playing golf, our method first estimates an aggressive propagation towards optimum using one network, and recurrently applies a residual CNN to learn the gradient of prior for delicate correction on restoration. Experiments show that our network achieves competitive performance on GoPro dataset, and our model is extremely lightweight compared with the state-of-art works.
Blind image deconvolution is the problem of recovering the latent image from the only observed blurry image when the blur kernel is unknown. In this paper, we propose an edge-based blur kernel estimation method for blind motion deconvolution. In our previous work, we incorporate both sparse representation and self-similarity of image patches as priors into our blind deconvolution model to regularize the recovery of the latent image. Since almost any natural image has properties of sparsity and multi-scale self-similarity, we construct a sparsity regularizer and a cross-scale non-local regularizer based on our patch priors. It has been observed that our regularizers often favor sharp images over blurry ones only for image patches of the salient edges and thus we define an edge mask to locate salient edges that we want to apply our regularizers. Experimental results on both simulated and real blurry images demonstrate that our method outperforms existing state-of-the-art blind deblurring methods even for handling of very large blurs, thanks to the use of the edge mask.
Total variation (TV) regularization has proven effective for a range of computer vision tasks through its preferential weighting of sharp image edges. Existing TV-based methods, however, often suffer from the over-smoothing issue and solution bias caused by the homogeneous penalization. In this paper, we consider addressing these issues by applying inhomogeneous regularization on different image components. We formulate the inhomogeneous TV minimization problem as a convex quadratic constrained linear programming problem. Relying on this new model, we propose a matching pursuit based total variation minimization method (MPTV), specifically for image deconvolution. The proposed MPTV method is essentially a cutting-plane method, which iteratively activates a subset of nonzero image gradients, and then solves a subproblem focusing on those activated gradients only. Compared to existing methods, MPTV is less sensitive to the choice of the trade-off parameter between data fitting and regularization. Moreover, the inhomogeneity of MPTV alleviates the over-smoothing and ringing artifacts, and improves the robustness to errors in blur kernel. Extensive experiments on different tasks demonstrate the superiority of the proposed method over the current state-of-the-art.
We investigate possibilities to speed up iterative algorithms for non-blind image deconvolution. We focus on algorithms in which convolution with the point-spread function to be deconvolved is used in each iteration, and aim at accelerating these convolution operations as they are typically the most expensive part of the computation. We follow two approaches: First, for some practically important specific point-spread functions, algorithmically efficient sliding window or list processing techniques can be used. In some constellations this allows faster computation than via the Fourier domain. Second, as iterations progress, computation of convolutions can be restricted to subsets of pixels. For moderate thinning rates this can be done with almost no impact on the reconstruction quality. Both approaches are demonstrated in the context of Richardson-Lucy deconvolution but are not restricted to this method.
In this paper, an iterative method for robust deconvolution with positivity constraints is discussed. It is based on the known variational interpretation of the Richardson-Lucy iterative deconvolution as fixed-point iteration for the minimisation of an information divergence functional under a multiplicative perturbation model. The asymmetric penaliser function involved in this functional is then modified into a robust penaliser, and complemented with a regulariser. The resulting functional gives rise to a fixed point iteration that we call robust and regularised Richardson-Lucy deconvolution. It achieves an image restoration quality comparable to state-of-the-art robust variational deconvolution with a computational efficiency similar to that of the original Richardson-Lucy method. Experiments on synthetic and real-world image data demonstrate the performance of the proposed method.
In this paper, we revisit the "FTVd" algorithm for Fast Total Variation Regularized Deconvolution, which has been widely used in the past few years. Both its original version implemented in the MATLAB software FTVd 3.0 and its related variant implemented in the latter version FTVd 4.0 are considered \cite{Wang08FTVdsoftware}. We propose that the intermediate results during the iterations are the solutions of a series of combined Tikhonov and total variation regularized image deconvolution models and therefore some of them often have even better image quality than the final solution, which is corresponding to the pure total variation regularized model.
We describe a learning-based approach to blind image deconvolution. It uses a deep layered architecture, parts of which are borrowed from recent work on neural network learning, and parts of which incorporate computations that are specific to image deconvolution. The system is trained end-to-end on a set of artificially generated training examples, enabling competitive performance in blind deconvolution, both with respect to quality and runtime.
In this work it is proposed a medical image segmentation pipeline for accurate bone segmentation from CT imaging. It is a two-step methodology, with a pre-segmentation step and a segmentation refinement step. First, the user performs a rough segmenting of the desired region of interest. Next, a fully automatic refinement step is applied to the pre-segmented data. The automatic segmentation refinement is composed by several sub-stpng, namely image deconvolution, image cropping and interpolation. The user-defined pre-segmentation is then refined over the deconvolved, cropped, and up-sampled version of the image. The algorithm is applied in the segmentation of CT images of a composite femur bone, reconstructed with different reconstruction protocols. Segmentation outcomes are validated against a gold standard model obtained with coordinate measuring machine Nikon Metris LK V20 with a digital line scanner LC60-D that guarantees an accuracy of 28 $\mu m$. High sub-pixel accuracy models were obtained for all tested Datasets. The algorithm is able to produce high quality segmentation of the composite femur regardless of the surface meshing strategy used.
Improving the quality of positron emission tomography (PET) images, affected by low resolution and high level of noise, is a challenging task in nuclear medicine and radiotherapy. This work proposes a restoration method, achieved after tomographic reconstruction of the images and targeting clinical situations where raw data are often not accessible. Based on inverse problem methods, our contribution introduces the recently developed total generalized variation (TGV) norm to regularize PET image deconvolution. Moreover, we stabilize this procedure with additional image constraints such as positivity and photometry invariance. A criterion for updating and adjusting automatically the regularization parameter in case of Poisson noise is also presented. Experiments are conducted on both synthetic data and real patient images.
High resolution ultrasound image reconstruction from a reduced number of measurements is of great interest in ultrasound imaging, since it could enhance both the frame rate and image resolution. Compressive deconvolution, combining compressed sensing and image deconvolution, represents an interesting possibility to consider this challenging task. The model of compressive deconvolution includes, in addition to the compressive sampling matrix, a 2D convolution operator carrying the information on the system point spread function. Through this model, the resolution of reconstructed ultrasound images from compressed measurements mainly depends on three aspects: the acquisition setup, i.e. the incoherence of the sampling matrix, the image regularization, i.e. the sparsity prior, and the optimization technique. In this paper, we mainly focused on the last two aspects. We proposed a novel simultaneous direction method of multipliers-based optimization scheme to invert the linear model, including two regularization terms expressing the sparsity of the RF images in a given basis and the generalized Gaussian statistical assumption on tissue reflectivity functions. The performance of the method is evaluated on both simulated and in vivo data.
In image deconvolution problems, the diagonalization of the underlying operators by means of the FFT usually yields very large speedups. When there are incomplete observations (e.g., in the case of unknown boundaries), standard deconvolution techniques normally involve non-diagonalizable operators, resulting in rather slow methods, or, otherwise, use inexact convolution models, resulting in the occurrence of artifacts in the enhanced images. In this paper, we propose a new deconvolution framework for images with incomplete observations that allows us to work with diagonalized convolution operators, and therefore is very fast. We iteratively alternate the estimation of the unknown pixels and of the deconvolved image, using, e.g., an FFT-based deconvolution method. This framework is an efficient, high-quality alternative to existing methods of dealing with the image boundaries, such as edge tapering. It can be used with any fast deconvolution method. We give an example in which a state-of-the-art method that assumes periodic boundary conditions is extended, through the use of this framework, to unknown boundary conditions. Furthermore, we propose a specific implementation of this framework, based on the alternating direction method of multipliers (ADMM). We provide a proof of convergence for the resulting algorithm, which can be seen as a "partial" ADMM, in which not all variables are dualized. We report experimental comparisons with other primal-dual methods, where the proposed one performed at the level of the state of the art. Four different kinds of applications were tested in the experiments: deconvolution, deconvolution with inpainting, superresolution, and demosaicing, all with unknown boundaries.
In this work, we propose a new approach for efficient edge-preserving image deconvolution. Our algorithm is based on a novel type of explicit image filter - guided filter. The guided filter can be used as an edge-preserving smoothing operator like the popular bilateral filter, but has better behaviors near edges. We propose an efficient iterative algorithm with the decouple of deblurring and denoising steps in the restoration process. In deblurring step, we proposed two cost function which could be computed with fast Fourier transform efficiently. The solution of the first one is used as the guidance image, and another solution will be filtered in next step. In the denoising step, the guided filter is used with the two obtained images for efficient edge-preserving filtering. Furthermore, we derive a simple and effective method to automatically adjust the regularization parameter at each iteration. We compare our deconvolution algorithm with many competitive deconvolution techniques in terms of ISNR and visual quality.
Image deconvolution is still to be a challenging ill-posed problem for recovering a clear image from a given blurry image, when the point spread function is known. Although competitive deconvolution methods are numerically impressive and approach theoretical limits, they are becoming more complex, making analysis, and implementation difficult. Furthermore, accurate estimation of the regularization parameter is not easy for successfully solving image deconvolution problems. In this paper, we develop an effective approach for image restoration based on one explicit image filter - guided filter. By applying the decouple of denoising and deblurring techniques to the deconvolution model, we reduce the optimization complexity and achieve a simple but effective algorithm to automatically compute the parameter in each iteration, which is based on Morozov's discrepancy principle. Experimental results demonstrate that the proposed algorithm outperforms many state-of-the-art deconvolution methods in terms of both ISNR and visual quality.
Computer vision tasks often have side information available that is helpful to solve the task. For example, for crowd counting, the camera perspective (e.g., camera angle and height) gives a clue about the appearance and scale of people in the scene. While side information has been shown to be useful for counting systems using traditional hand-crafted features, it has not been fully utilized in counting systems based on deep learning. In order to incorporate the available side information, we propose an adaptive convolutional neural network (ACNN), where the convolutional filter weights adapt to the current scene context via the side information. In particular, we model the filter weights as a low-dimensional manifold, parametrized by the side information, within the high-dimensional space of filter weights. With the help of side information and adaptive weights, the ACNN can disentangle the variations related to the side information, and extract discriminative features related to the current context. Since existing crowd counting datasets do not contain ground-truth side information, we collect a new dataset with the ground-truth camera angle and height as the side information. On experiments in crowd counting, the ACNN improves counting accuracy compared to a plain CNN with a similar number of parameters. We also apply ACNN to image deconvolution to show its potential effectiveness on other computer vision applications.
In this paper, we propose a fully convolutional networks for iterative non-blind deconvolution We decompose the non-blind deconvolution problem into image denoising and image deconvolution. We train a FCNN to remove noises in the gradient domain and use the learned gradients to guide the image deconvolution step. In contrast to the existing deep neural network based methods, we iteratively deconvolve the blurred images in a multi-stage framework. The proposed method is able to learn an adaptive image prior, which keeps both local (details) and global (structures) information. Both quantitative and qualitative evaluations on benchmark datasets demonstrate that the proposed method performs favorably against state-of-the-art algorithms in terms of quality and speed.
Approximation theory plays an important role in image processing, especially image deconvolution and decomposition. For piecewise smooth images, there are many methods that have been developed over the past thirty years. The goal of this study is to devise similar and practical methodology for handling textured images. This problem is motivated by forensic imaging, since fingerprints, shoeprints and bullet ballistic evidence are textured images. In particular, it is known that texture information is almost destroyed by a blur operator, such as a blurred ballistic image captured from a low-cost microscope. The contribution of this work is twofold: first, we propose a mathematical model for textured image deconvolution and decomposition into four meaningful components, using a high-order partial differential equation approach based on the directional mean curvature. Second, we uncover a link between functional analysis and multiscale sampling theory, e.g., harmonic analysis and filter banks. Both theoretical results and examples with natural images are provided to illustrate the performance of the proposed model.
We propose a robust image enhancement algorithm dedicated for muscle fiber specimen images captured by optical microscopes. Blur or out of focus problems are prevalent in muscle images during the image acquisition stage. Traditional image deconvolution methods do not work since they assume the blur kernels are known and also produce ring artifacts. We provide a compact framework which involves a novel spatially non-uniform blind deblurring approach specialized to muscle images which automatically detects and alleviates degraded regions. Ring artifacts problems are addressed and a kernel propagation strategy is proposed to speedup the algorithm and deals with the high non-uniformity of the blur kernels on muscle images. Experiments show that the proposed framework performs well on muscle images taken with modern advanced optical microscopes. Our framework is free of laborious parameter settings and is computationally efficient.
While variational methods have been among the most powerful tools for solving linear inverse problems in imaging, deep (convolutional) neural networks have recently taken the lead in many challenging benchmarks. A remaining drawback of deep learning approaches is their requirement for an expensive retraining whenever the specific problem, the noise level, noise type, or desired measure of fidelity changes. On the contrary, variational methods have a plug-and-play nature as they usually consist of separate data fidelity and regularization terms. In this paper we study the possibility of replacing the proximal operator of the regularization used in many convex energy minimization algorithms by a denoising neural network. The latter therefore serves as an implicit natural image prior, while the data term can still be chosen independently. Using a fixed denoising neural network in exemplary problems of image deconvolution with different blur kernels and image demosaicking, we obtain state-of-the-art reconstruction results. These indicate the high generalizability of our approach and a reduction of the need for problem-specific training. Additionally, we discuss novel results on the analysis of possible optimization algorithms to incorporate the network into, as well as the choices of algorithm parameters and their relation to the noise level the neural network is trained on.