Deep learning-based image super-resolution considering quantitative and perceptual quality

Jun Ho Choi, Jun Hyuk Kim, Manri Cheon, Jong Seok Lee

Research output: Contribution to journalArticle

Abstract

Recently, it has been shown that in super-resolution, there exists a tradeoff relationship between the quantitative and perceptual quality of super-resolved images, which correspond to the similarity to the ground-truth images and the naturalness, respectively. In this paper, we propose a novel super-resolution method that can improve the perceptual quality of the upscaled images while preserving the conventional quantitative performance. The proposed method employs a deep network for multi-pass upscaling in company with a discriminator network and two qualitative score predictor networks. Experimental results demonstrate that the proposed method achieves a good balance of the quantitative and perceptual quality, showing more satisfactory results than existing methods.

Original languageEnglish
Pages (from-to)347-359
Number of pages13
JournalNeurocomputing
Volume398
DOIs
Publication statusAccepted/In press - 2019 Jan 1

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Deep learning-based image super-resolution considering quantitative and perceptual quality'. Together they form a unique fingerprint.

  • Cite this