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

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

*此作品的通信作者

研究成果: 期刊稿件文章同行評審

450 引文 斯高帕斯(Scopus)

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
158
DOIs
出版狀態已出版 - 01 05 2017
對外發佈

文獻附註

Publisher Copyright:
© 2017 Elsevier Inc.

指紋

深入研究「Learning a no-reference quality metric for single-image super-resolution」主題。共同形成了獨特的指紋。

引用此