Year-end Sale % OFF 
Abstract
Prior knowledge plays an important role in the process of image super-resolution reconstruction, which can constrain the solution space efficiently. In this paper, we utilized the fact that clear image exhibits stronger self-similarity property than other degradated version to present a new prior called maximizing nonlocal self-similarity for single image super-resolution. For describing the prior with mathematical language, a joint Gaussian mixture model was trained with LR and HR patch pairs extracted from the input LR image and its lower scale, and the prior can be described as a specific Gaussian distribution by derivation. In our algorithm, a large scale of sophisticated training and time-consuming nearest neighbor searching is not necessary, and the cost function of this algorithm shows closed form solution. The experiments conducted on BSD500 and other popular images demonstrate that the proposed method outperforms traditional methods and is competitive with the current state-of-the-art algorithms in terms of both quantitative metrics and visual quality.
Highlights
The technology of single image super-resolution (SISR) has been widely used in many fields, such as medical imaging, remote sensing and digital home etc., which refers to estimating the corresponding high-resolution (HR) image just according to an input low resolution (LR) one through software computing way
7, and 8, these three groups of images are the comparison results of these algorithms that are magnified by 2 times, 3 times, and 4 times separately. Observing these three groups of images carefully, we can notice that the algorithms of ScSR, Glasner, Gaussian process regression (GPR), and SPM did not preserve the edges well and made noise, artifacts, and distortion along the salient edges in the reconstructed HR images
By observing the smallest windows marked in the reconstructed results, it can be found that our method has the smallest deformation near the edge, which is closest to the original image and shows excellent texture processing capability
Summary
The technology of single image super-resolution (SISR) has been widely used in many fields, such as medical imaging, remote sensing and digital home etc., which refers to estimating the corresponding high-resolution (HR) image just according to an input low resolution (LR) one through software computing way. Due to the one-to-many mapping relationship between the LR and HR images captured from the same scene, the process from LR image to HR one is obviously a typically ill-posed problem. For obtaining HR image with sharp edges and fine details, researchers generally introduce some priors explicitly or implicitly to impose on the inverse imaging process; the quality of the reconstructed HR image is closely related to the introduced priors. The common priors for SISR include edge prior [1], gradient profile prior [2], sparse prior [3, 4], etc. There are mainly three categories of SISR approaches including interpolation-based methods, reconstruction-based methods, and learning-based methods
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
