Learning a no-reference quality metric for single-image super-resolution

Chao Ma, Chih Yuan Yang, Xiaokang Yang, Ming Hsuan Yang

Research output: Contribution to journalArticlepeer-review

146 Citations (Scopus)

Abstract

Numerous single-image super-resolution algorithms have been proposed in the literature, but few studies address the problem of performance evaluation based on visual perception. While most super-resolution images are evaluated by full-reference metrics, the effectiveness is not clear and the required ground-truth images are not always available in practice. To address these problems, we conduct human subject studies using a large set of super-resolution images and propose a no-reference metric learned from visual perceptual scores. Specifically, we design three types of low-level statistical features in both spatial and frequency domains to quantify super-resolved artifacts, and learn a two-stage regression model to predict the quality scores of super-resolution images without referring to ground-truth images. Extensive experimental results show that the proposed metric is effective and efficient to assess the quality of super-resolution images based on human perception.

Original languageEnglish
Pages (from-to)1-16
Number of pages16
JournalComputer Vision and Image Understanding
Volume158
DOIs
Publication statusPublished - 2017 May 1

Bibliographical note

Funding Information:
This work is supported in part by The National Key Research and Development Program of China (2016YFB1001003), NSFC (61527804, 61521062), STCSM (14XD1402100) and the 111 Program (B07022).

Publisher Copyright:
© 2017 Elsevier Inc.

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Learning a no-reference quality metric for single-image super-resolution'. Together they form a unique fingerprint.

Cite this