Superresolution image reconstruction using fast inpainting algorithms

Abstract

The main aim of this paper is to employ the total variation (TV) inpainting model to superresolution imaging problems. We focus on the problem of reconstructing a high-resolution image from several decimated, blurred and noisy low-resolution versions of the high-resolution image. We propose a general framework for multiple shifted and multiple blurred low-resolution image frames which subsumes several well-known superresolution models. Moreover, our framework allows an arbitrary pattern of missing pixels and in particular missing frames. The proposed model combines the TV inpainting model with the framework to formulate the superresolution image reconstruction problem as an optimization problem. A distinct feature of our model is that in regions without missing pixels, the reconstruction process is regularized by TV minimization whereas in regions with missing pixels or missing frames, they are reconstructed automatically by means of TV inpainting. A fast algorithm based on fixed-point iterations and preconditioning techniques is investigated to solve the associated Euler-Lagrange equations. Experimental results are given to show that the proposed TV superresolution imaging model is effective and the proposed algorithm is efficient.

Total variation super resolution using a variational approach

“…Recently, motivated by its success in image recovery problems, the use of the total variation (TV) function and its variants has become popular in super resolution. Both regularization-based [2,3] and Bayesian [4] formulations have been proposed which utilize TV functions to characterize the HR images. However, both of these approaches involve certain model parameters to be set by the user, which is in general a difficult task.…”

Image super-resolution representation via image patches based on extreme learning machine

“…In the experiment, s=2 and L=3. In these comparisons, multi-frame super-resolutions are encountered, which are described as "multi frame, no blur" and "single frame, multi blur" respectively in [12]. The results of the proposed method were average values of 20 repeats respectively.…”

“…In the comparisons with image reconstruction using fast image inpainting algorithms [12], the testing image was the classic 126 126  Camera picture used in [12]. In the experiment, s=2 and L=3.…”

“…The results were compared to traditional interpolations such as bilinear and bicubic interpolation. In multi-frame tests, results were compared to that of image reconstruction using fast image inpainting algorithms [12], a late research in reconstructions.…”

“…In Section II, the algorithm of ELM is briefly introduced. The technical approach to implement the proposed method is described in Section III and the experimental sets and results are shown in Section IV, as well as comparisons to traditional interpolations and image reconstruction using fast image inpainting algorithms, a late research in reconstruction-based methods [12]. And finally in Section V, this paper is concluded and a few of interesting topics are proposed for future works.…”