Bilateral Spectrum Weighted Total Variation for Noisy-Image Super-Resolution and Image Denoising

Low-Rank Total Variation for Image Super-Resolution

Most natural images can be approximated using their low-rank components. This fact has'been successfully exploited in recent advancements of matrix completion algorithms for image recovery. However, a major limitation of low-rank matrix completion algorithms is that they cannot recover the case where a whole row or column is missing. The missing row or column will be simply filled as an arbitra...

Total variation based image denoising and restoration

This paper is devoted to the total variation (TV) based approach to image denoising and restoration. The restored image minimizes total variation in the class of images which satisfy the contraints given by the image acquisition model. We compute some explicit solutions of the denoising model which explain some of the features observed in numerical experiments. We also comment on some alternati...

Image Segmentation and Total Variation Denoising

Learning-Based Document Image Super-Resolution with Directional Total Variation

We propose a super-resolution algorithm based on local adaptation. In the proposed algorithm, the mapping function from the low-resolution images to high-resolution image is estimated by adaptation. Moreover, the property of the high-resolution image is learned and incorporated in a regularization -based restoration. The proposed regularization function is used as a general directional total va...

DCGANs for image super-resolution, denoising and debluring

Advance of computational power and big datasets brings the opportunity of using deep learning methods to do image processing. We used deep convolutional generative adversarial networks (DCGAN) to do various image processing tasks such as super-resolution, denoising and deconvolution. DCGAN allows us to use a single architecture to do different image processing tasks and achieve competitive PSNR...