ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution

TL;DR

ERQA is a new metric designed to evaluate the quality of restored details in video super-resolution, focusing on edge fidelity to ensure trustworthy and accurate detail restoration.

Contribution

The paper introduces ERQA, a novel edge-based quality assessment metric specifically for video super-resolution, validated on a challenging benchmark dataset.

Findings

ERQA effectively correlates with perceived detail fidelity.

It outperforms existing metrics in detecting detail restoration quality.

The metric is publicly available for use and further research.

Abstract

Despite the growing popularity of video super-resolution (VSR), there is still no good way to assess the quality of the restored details in upscaled frames. Some SR methods may produce the wrong digit or an entirely different face. Whether a method's results are trustworthy depends on how well it restores truthful details. Image super-resolution can use natural distributions to produce a high-resolution image that is only somewhat similar to the real one. VSR enables exploration of additional information in neighboring frames to restore details from the original scene. The ERQA metric, which we propose in this paper, aims to estimate a model's ability to restore real details using VSR. On the assumption that edges are significant for detail and character recognition, we chose edge fidelity as the foundation for this metric. Experimental validation of our work is based on the MSU Video Super-Resolution Benchmark, which includes the most difficult patterns for detail restoration and verifies the fidelity of details from the original frame. Code for the proposed metric is publicly available at https://github.com/msu-video-group/ERQA.