Kernel Estimation Using Total Variation Guided GAN for Image Super-Resolution

Various super-resolution (SR) kernels in the degradation model deteriorate the performance of the SR algorithms, showing unpleasant artifacts in the output images. Hence, SR kernel estimation has been studied to improve the SR performance in several ways for more than a decade. In particular, a conventional research named KernelGAN has recently been proposed. To estimate the SR kernel from a single image, KernelGAN introduces generative adversarial networks(GANs) that utilize the recurrence of similar structures across scales. Subsequently, an enhanced version of KernelGAN, named E-KernelGAN, was proposed to consider image sharpness and edge thickness. Although it is stable compared to the earlier method, it still encounters challenges in estimating sizable and anisotropic kernels because the structural information of an input image is not sufficiently considered. In this paper, we propose a kernel estimation algorithm called Total Variation Guided KernelGAN (TVG-KernelGAN), which efficiently enables networks to focus on the structural information of an input image. The experimental results show that the proposed algorithm accurately and stably estimates kernels, particularly sizable and anisotropic kernels, both qualitatively and quantitatively. In addition, we compared the results of the non-blind SR methods, using SR kernel estimation techniques. The results indicate that the performance of the SR algorithms was improved using our proposed method.

Automated summary

To improve the performance of super-resolution algorithms, various SR kernel models have been proposed. However, they lead to unpleasant artifacts in the output images. KernelGAN, a conventional research, introduces GANs to estimate SR kernels from single images. However, it still faces challenges in estimating large-sized and anisotropic kernels due to the insufficient consideration of structural information. Therefore, this paper proposes a kernel estimation algorithm called TVG-KernelGAN, which efficiently focuses on the structural information of input images. Experimental results show that the proposed method accurately and stably estimates kernels and improves the performance of super-resolution algorithms.