Rank-based No-reference Quality Assessment for Face Swapping

TL;DR

This paper introduces a novel no-reference image quality assessment method tailored for face swapping, leveraging a large dataset, facial attribute ranking, and a Siamese network to achieve state-of-the-art performance.

Contribution

It presents a new NR-IQA approach for face swapping that outperforms existing metrics and enhances face-swapping models in expression and pose accuracy.

Findings

Achieved state-of-the-art quality assessment performance.

Outperformed existing no-reference IQA metrics.

Enabled improved face-swapping with better expression and pose handling.

Abstract

Face swapping has become a prominent research area in computer vision and image processing due to rapid technological advancements. The metric of measuring the quality in most face swapping methods relies on several distances between the manipulated images and the source image, or the target image, i.e., there are suitable known reference face images. Therefore, there is still a gap in accurately assessing the quality of face interchange in reference-free scenarios. In this study, we present a novel no-reference image quality assessment (NR-IQA) method specifically designed for face swapping, addressing this issue by constructing a comprehensive large-scale dataset, implementing a method for ranking image quality based on multiple facial attributes, and incorporating a Siamese network based on interpretable qualitative comparisons. Our model demonstrates the state-of-the-art performance in the quality assessment of swapped faces, providing coarse- and fine-grained. Enhanced by this metric, an improved face-swapping model achieved a more advanced level with respect to expressions and poses. Extensive experiments confirm the superiority of our method over existing general no-reference image quality assessment metrics and the latest metric of facial image quality assessment, making it well suited for evaluating face swapping images in real-world scenarios.