摘要
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.
原文 | 英語 |
---|---|
頁(從 - 到) | 1-16 |
頁數 | 16 |
期刊 | Computer Vision and Image Understanding |
卷 | 158 |
DOIs | |
出版狀態 | 已出版 - 01 05 2017 |
對外發佈 | 是 |
文獻附註
Publisher Copyright:© 2017 Elsevier Inc.