Improvement of Luminance Isotropy for Convolutional Neural Networks-Based Image Super-Resolution
Authors:
- 1 July 2020
- journal article
- research article
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
- Vol. E103.A (7) , 955-958
Abstract
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.Keywords
This publication has 10 references indexed in Scilit:
- Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution2017
- Multi-Channel Convolutional Neural Networks for Image Super-ResolutionIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2017
- Sketch-based manga retrieval using manga109 datasetMultimedia Tools and Applications, 2016
- MatConvNet2015
- Single image super-resolution from transformed self-exemplars2015
- Image Super-Resolution Using Deep Convolutional NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Caffe2014
- On Single Image Scale-Up Using Sparse-Representations2012
- Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding2012
- Image Super-Resolution Via Sparse RepresentationIEEE Transactions on Image Processing, 2010