The search functionality is under construction.
The search functionality is under construction.

Improvement of Luminance Isotropy for Convolutional Neural Networks-Based Image Super-Resolution

Kazuya URAZOE, Nobutaka KUROKI, Yu KATO, Shinya OHTANI, Tetsuya HIROSE, Masahiro NUMA

  • Full Text Views

    0

  • Cite this

Summary :

Convolutional neural network (CNN)-based image super-resolutions are widely used as a high-quality image-enhancement technique. However, in general, they show little to no luminance isotropy. Thus, we propose two methods, “Luminance Inversion Training (LIT)” and “Luminance Inversion Averaging (LIA),” to improve the luminance isotropy of CNN-based image super-resolutions. Experimental results of 2× image magnification show that the average peak signal-to-noise ratio (PSNR) using Luminance Inversion Averaging is about 0.15-0.20dB higher than that for the conventional super-resolution.

Publication
IEICE TRANSACTIONS on Fundamentals Vol.E103-A No.7 pp.955-958
Publication Date
2020/07/01
Publicized
Online ISSN
1745-1337
DOI
10.1587/transfun.2019EAL2168
Type of Manuscript
LETTER
Category
Image

Authors

Kazuya URAZOE
  Kobe University
Nobutaka KUROKI
  Kobe University
Yu KATO
  Kobe University
Shinya OHTANI
  Kobe University
Tetsuya HIROSE
  Kobe University
Masahiro NUMA
  Kobe University

Keyword