Recently, deep neural networks have been successfully applied for removing rain streaks from images. However, these methods did not consider the relationships between the skip layers. In order to improve the deraining performance and use the information of different layers, we propose to construct connections between different layers and propose a residual skip connection neural network for single image deraining. Then we train the network on synthesized data. Both experiments on synthesized and real-world images show the proposed method outperforms state-of-the-art methods in terms of rain streak removal and image information preservation.
This paper mainly focuses on the rain streak removal task from a single image. Based on the observation that the distribution of rain streak in an image is sparse. We propose a two- phase single image deraining method. Firstly, it detects the rain locations with a proposed anisotropic global gradient prior (AGGP) and generates a rain mask for rain streak removal. Then it recovers the information in rain distorted region with AGGP based multi-layer image inpainting model. Furthermore, to solve the multi-variable optimization problems, we develop an alternating half-quadratic algorithm by introducing alternating algorithm and the variable split method. Both experiments on synthesized and realworld images show the proposed method outperforms state-of-the-art methods in terms of rain streak removal and image multi-layer information preservation.
Image deblurring and inpainting are traditional image processing problems, and the effects achieved for high-resolution images are not satisfactory. In recent years, Convolutional Sparse coding (CSC) has been received more attention and introduced into image processing, such as blind deblurring. However, none of the works address the issue containing both blur and inpainting. In this work, we propose a novel framework of CSC for simultaneous image deblurring and inpainting. First, we learn a dictionary instead of applying a given dictionary for better image representation. Second, we use the learned dictionary with the ℓ1 norm to regularize images. In addition, we apply a total anisotropic variation to enhance the edges of the image. Usually, we use the alternating direction method of multipliers (ADMM) formulation in the Fourier domain for the dictionary. We demonstrate the proposed training scheme for simultaneous image deblurring and inpainting, achieving state-of-the-art results.
In this paper, we address the rain streak removal from a single image. In order to efficiently detect and remove the annoying rain streaks, we propose a global single-directional gradient prior with the L0 norm to model the rain streak. To preserve the abundant information of the background, we learn a convolutional sparse coding (CSC) to represent the background. Furthermore, we develop an alternating direction method of multipliers (ADMM) to solve multi-variable optimization problems. Experiments on synthesized and real-world images show that the proposed method outperforms state-of-art methods in terms of rain streak removal and background preservation.
Outdoor imaging often suffers from the negative effects of the rain streaks, which would lead to the distortion of image contents. Most of the existing deraining approaches propose to build prior models to formulate the appearance of rain streaks and image features. However, these works deal with the rain streaks removal on the whole image regions. This may lead to the image regions without rain streaks distorted. In this paper, we proposed a new method for simultaneously investigating the candidates of rain streaks and image restoration. We use the L0 sparsity regularization for rain region estimation , and apply the framelet with L0 norm to protect the sharpen images. Our method only processes the regions with rain streaks and leaves other regions free. Experimental results demonstrate the effectiveness of our approach on rain streak removal and image restoration.
Images are often corrupted by impulse noise due to transmission errors, malfunctioning pixel elements in camera sensors, faulty memory locations in the imaging process. This paper proposes a new method for removing the mixed impulse noise and gaussian noise. The proposed method has two-phase, and the first phase is to identify candidate pixels existing impulse noise by using median filtering. The second phase processes the regions with impulse noise and leaves the others free with a mask generated by the previous phase. In order to protect the sharp image, we propose a L0 regularized framelet with a L1 fidelity term to recover the images. Numerical results demonstrate that the proposed method is a significantly advance over several state-of-the-art techniques on restoration performance.
Images are often corrupted by impulse noise due to transmission errors, malfunctioning pixel elements in camera sensors, faulty memory locations in the imaging process. This paper proposes a two-phase method for impulse noise. In the first phase, a suitable noise is applied to identify the image pixels contaminated by noise. Then, in the second phase, based upon the information on the location of noise-free pixels, images are recovered by using a structure decomposition denoising method. In order to solve the denoising model, split bregman iteration combined with alternating minimization algorithm is utilized. Numerical results demonstrate that the proposed method is a significantly advance over several state-of-the-art techniques on restoration performance.
Image deblurring is a fundamental problem in image processing. Conventional methods often deal with the degraded image as a whole while ignoring that an image contains two different components: cartoon and texture. Recently, total variation (TV) based image decomposition methods are introduced into image deblurring problem. However, these methods often suffer from the well-known stair-casing effects of TV. In this paper, a new cartoon -texture based sparsity regularization method is proposed for non-blind image deblurring. Based on image decomposition, it respectively regularizes the cartoon with a combined term including framelet-domain-based sparse prior and a quadratic regularization and the texture with the sparsity of discrete cosine transform domain. Then an adaptive alternative split Bregman iteration is proposed to solve the new multi-term sparsity regularization model. Experimental results demonstrate that our method can recover both cartoon and texture of images simultaneously, and therefore can improve the visual effect, the PSNR and the SSIM of the deblurred image efficiently than TV and the undecomposed methods.
Real images usually have two layers, namely, cartoons(the piece-wise smooth part of image) and textures(the oscillating
pattern part of the image). In this paper, we solve the challenging image deconvolution problems by using variation
image decomposition method which can regularize the cartoon with total variation and texture in G space respectively.
Different from existing schemes in the literature which can only recover the smooth structure of the image, our
deconvolution method can not only restore the smooth part of image but also recover the detailed oscillating part of the
image. Numerical simulation examples are given to demonstrate the applicability and usefulness of our proposed
algorithms in image deconvolution.
In order to study light scattering from randomly rough surface, the linear filtering method is used to generate Gaussian randomly rough surface, and the method of moments is used to calculate the scattering light intensity distribution from perfect conduct and dielectric surfaces. The calculation results show that scattering characteristics between conductor and dielectric surfaces exist several significant differences: (1) the scattering peak value of perfectly conduct is larger than scattering peak value of dielectric on the same roughness; (2) the difference between s- and ppolarized scattering results are rather small in perfectly conduct randomly rough surfaces, while there is a obvious difference between s- and p-polarized scattering results in the condition of dielectric randomly rough surfaces; (3) though in both conditions of perfectly conduct and dielectric randomly rough surfaces, there is a shift from specular to backscattering direction when incident is p-polarized light, however, in dielectric randomly rough surface situation, the shift is much more obvious than in conduct situation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.