Learning-Based Quality Assessment for Image Super-Resolution

TL;DR

This paper introduces a large-scale SR image quality database and a deep learning-based quality assessment model that outperform existing metrics and generalize well across different datasets.

Contribution

The work presents the creation of the SISAR database and a novel end-to-end deep learning model for SR image quality assessment, addressing limitations of current metrics.

Findings

The DISQ model outperforms state-of-the-art quality metrics.

The SISAR database is the largest SR-IQA database to date.

The model demonstrates strong cross-database generalization.

Abstract

Image Super-Resolution (SR) techniques improve visual quality by enhancing the spatial resolution of images. Quality evaluation metrics play a critical role in comparing and optimizing SR algorithms, but current metrics achieve only limited success, largely due to the lack of large-scale quality databases, which are essential for learning accurate and robust SR quality metrics. In this work, we first build a large-scale SR image database using a novel semi-automatic labeling approach, which allows us to label a large number of images with manageable human workload. The resulting SR Image quality database with Semi-Automatic Ratings (SISAR), so far the largest of SR-IQA database, contains 8,400 images of 100 natural scenes. We train an end-to-end Deep Image SR Quality (DISQ) model by employing two-stream Deep Neural Networks (DNNs) for feature extraction, followed by a feature fusion network for quality prediction. Experimental results demonstrate that the proposed method outperforms state-of-the-art metrics and achieves promising generalization performance in cross-database tests. The SISAR database and DISQ model will be made publicly available to facilitate reproducible research.