DSRGAN: Detail Prior-Assisted Perceptual Single Image Super-Resolution via Generative Adversarial Networks

Page view(s)
23
Checked on Jun 08, 2024
DSRGAN: Detail Prior-Assisted Perceptual Single Image Super-Resolution via Generative Adversarial Networks
Title:
DSRGAN: Detail Prior-Assisted Perceptual Single Image Super-Resolution via Generative Adversarial Networks
Journal Title:
IEEE Transactions on Circuits and Systems for Video Technology
Publication Date:
04 July 2022
Citation:
Liu, Z., Li, Z., Wu, X., Liu, Z., & Chen, W. (2022). DSRGAN: Detail Prior-Assisted Perceptual Single Image Super-Resolution via Generative Adversarial Networks. IEEE Transactions on Circuits and Systems for Video Technology, 32(11), 7418–7431. https://doi.org/10.1109/tcsvt.2022.3188433
Abstract:
The generative adversarial network (GAN) is successfully applied to study the perceptual single image superresolution (SISR). However, since the GAN is data-driven, it has a fundamental limitation on restoring real high frequency information for an unknown instance (or image) during test. On the other hand, the conventional model-based methods have a superiority to achieve instance adaptation as they operate by considering the statistics of each instance (or image) only. Motivated by this, we propose a novel model-based algorithm, which can extract the detail layer of an image efficiently. The detail layer represents the high frequency information of image and it is constituted of image edges and fine textures. It is seamlessly incorporated into the GAN and serves as a prior knowledge to assist the GAN in generating more realistic details. The proposed method, named DSRGAN, takes advantages from both the model-based conventional algorithm and the data-driven deep learning network. Experimental results demonstrate that the DSRGAN outperforms the state-of-the-art SISR methods on perceptual metrics, meanwhile achieving comparable results in terms of fidelity metrics. Following the DSRGAN, it is feasible to incorporate other conventional image processing algorithms into a deep learning network to form a model-based deep SISR
License type:
Publisher Copyright
Funding Info:
There was no specific funding for the research done
Description:
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
1558-2205
1051-8215
Files uploaded:

File Size Format Action
dsrgan-1223.pdf 9.70 MB PDF Open