Open AccessSingle image super-resolution via Image Quality Assessment-Guided Deep Learning Network
Author(s) -
Zhengqiang Xiong,
Manhui Lin,
Zhen Lin,
Tao Sun,
Guangyi Yang,
Zhenxing Wang
Publication year - 2020
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0241313
Subject(s) - computer science , benchmark (surveying) , artificial intelligence , pairwise comparison , distortion (music) , image quality , image (mathematics) , ranking (information retrieval) , pattern recognition (psychology) , pixel , deep learning , process (computing) , data mining , machine learning , amplifier , computer network , geodesy , bandwidth (computing) , geography , operating system
In recent years, deep learning (DL) networks have been widely used in super-resolution (SR) and exhibit improved performance. In this paper, an image quality assessment (IQA)-guided single image super-resolution (SISR) method is proposed in DL architecture, in order to achieve a nice tradeoff between perceptual quality and distortion measure of the SR result. Unlike existing DL-based SR algorithms, an IQA net is introduced to extract perception features from SR results, calculate corresponding loss fused with original absolute pixel loss, and guide the adjustment of SR net parameters. To solve the problem of heterogeneous datasets used by IQA and SR networks, an interactive training model is established via cascaded network. We also propose a pairwise ranking hinge loss method to overcome the shortcomings of insufficient samples during training process. The performance comparison between our proposed method with recent SISR methods shows that the former achieves a better tradeoff between perceptual quality and distortion measure than the latter. Extensive benchmark experiments and analyses also prove that our method provides a promising and opening architecture for SISR, which is not confined to a specific network model.