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

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 require...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computer vision and image understanding Ročník 158; s. 1 - 16
Hlavní autoři: Ma, Chao, Yang, Chih-Yuan, Yang, Xiaokang, Yang, Ming-Hsuan
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Inc 01.05.2017
Témata:
ISSN:1077-3142, 1090-235X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
ISSN:1077-3142
1090-235X
DOI:10.1016/j.cviu.2016.12.009