Journal
COMPUTER VISION AND IMAGE UNDERSTANDING
Volume 158, Issue -, Pages 1-16Publisher
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.cviu.2016.12.009
Keywords
Image quality assessment; No-reference metric; Single-image super-resolution
Funding
- National Key Research and Development Program of China [2016YFB1001003]
- NSFC [61527804, 61521062]
- STCSM [14XD1402100]
- 111 Program [B07022]
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1149783] Funding Source: National Science Foundation
Ask authors/readers for more resources
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. (C) 2017 Elsevier Inc. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available