Learning a No-Reference Quality Metric for Single-Image Super-Resolution
This addresses the problem of assessing super-resolution image quality without ground-truth for researchers and practitioners, though it is incremental as it builds on existing feature-based methods.
The paper tackles the lack of perceptual evaluation for single-image super-resolution by proposing a no-reference metric learned from human scores, showing it is effective and efficient in experiments.
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 fullreference 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.