To Learn Image Super-Resolution, Use a GAN to Learn How to Do Image Degradation First

Bulat, Adrian; Yang, Jing; Tzimiropoulos, Georgios

Abstract

This paper is on image and face super-resolution. The vast majority of prior work for this problem focus on how to increase the resolution of low-resolution images which are artificially generated by simple bilinear down-sampling (or in a few cases by blurring followed by down-sampling). We show that such methods fail to produce good results when applied to real-world low-resolution, low quality images. To circumvent this problem, we propose a two-stage process which firstly trains a High-to-Low Generative Adversarial Network (GAN) to learn how to degrade and downsample high-resolution images requiring, during training, only unpaired high and low-resolution images. Once this is achieved, the output of this network is used to train a Low-to-High GAN for image super-resolution using this time paired low- and high-resolution images. Our main result is that this network can be now used to effectively increase the quality of real-world low-resolution images. We have applied the proposed pipeline for the problem of face super-resolution where we report large improvement over baselines and prior work although the proposed method is potentially applicable to other object categories.

Citation

Bulat, A., Yang, J., & Tzimiropoulos, G. (2018, September). To Learn Image Super-Resolution, Use a GAN to Learn How to Do Image Degradation First. Presented at 15th European Conference on Computer Vision, Munich, Germany

• Presentation Conference Type: Edited Proceedings
• Conference Name: 15th European Conference on Computer Vision
• Start Date: Sep 8, 2018
• End Date: Sep 14, 2018
• Acceptance Date: Jul 3, 2018
• Online Publication Date: Oct 5, 2018
• Publication Date: Oct 6, 2018
• Deposit Date: Oct 15, 2018
• Publicly Available Date: Oct 15, 2018
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Volume: 11210 LNCS
• Pages: 187-202
• Series Title: Lecture Notes in Computer Science
• Series Number: 11210
• Series ISSN: 1611-3349
• Book Title: Computer Vision – ECCV 2018: 15th European Conference Munich, Germany, September 8–14, 2018 Proceedings, Part VI
• ISBN: 9783030012304
• DOI: https://doi.org/10.1007/978-3-030-01231-1_12
• Keywords: Image and face super-resolution; Generative Adversarial Networks; GANs
• Public URL: https://nottingham-repository.worktribe.com/output/1164422
• Publisher URL: https://link.springer.com/chapter/10.1007/978-3-030-01231-1_12
• Contract Date: Oct 15, 2018