Title: Self-similarity single image super-resolution based on blur kernel estimation for texture reconstruction

Authors: Kawther Aarizou; Abdelhamid Loukil

Addresses: Electronics Department, Intelligent Systems Research Laboratory (LARESI), Université des Sciences et de la Technologie d'Oran Mohamed Boudiaf, Oran, Algeria ' Electronics Department, Intelligent Systems Research Laboratory (LARESI), Université des Sciences et de la Technologie d'Oran Mohamed Boudiaf, Oran, Algeria

Abstract: Most recent single image super resolution (SISR) reconstruction methods adopt simple bicubic downsampling to construct low-resolution (LR) and high-resolution (HR) pairs for training. Those models learn an inverted version of an ideal degradation operation which leads to generating less realistic SR images. The obtained details are either blurred or not reminiscent of the usually observed textures Du et al. (2020). The generation of SR image from a single LR with faithful ground-truth texture and no external information remains an issue, especially when the degradation model is not defined (not necessarily bicubic downscaling). To overcome this issue, we focus on designing a single-image SR reconstruction framework for real-world scenarios by injecting the image-specific degradation kernel in the training process. Our method combines the advantages of both SISR and multiple-image super resolution (MISR) techniques by generating a dataset regarding internal statistic of the LR image. A small CNN is trained over this internal dataset and requires no additional or external data. Our method is proved to address more textural details in the generated outcome, and outperforms state-of-the-art deep models.

Keywords: unsupervised single-image super-resolution; internal learning; image-specific super resolution; data-augmentation; kernel estimation.

DOI: 10.1504/IJCSE.2022.120791

International Journal of Computational Science and Engineering, 2022 Vol.25 No.1, pp.64 - 73

Received: 24 Oct 2020
Accepted: 21 Apr 2021
Published online: 08 Feb 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article