IFQA: Interpretable Face Quality Assessment

TL;DR

This paper introduces IFQA, a face-centric, interpretable image quality assessment metric based on an adversarial framework, emphasizing facial regions and improving over existing metrics in face restoration tasks.

Contribution

The paper presents a novel face-oriented quality assessment metric with a per-pixel discriminator, enhancing interpretability and effectiveness in face restoration evaluation.

Findings

IFQA outperforms existing face quality metrics.

The face-centric approach improves assessment accuracy.

Using IFQA as an objective function enhances restoration performance.

Abstract

Existing face restoration models have relied on general assessment metrics that do not consider the characteristics of facial regions. Recent works have therefore assessed their methods using human studies, which is not scalable and involves significant effort. This paper proposes a novel face-centric metric based on an adversarial framework where a generator simulates face restoration and a discriminator assesses image quality. Specifically, our per-pixel discriminator enables interpretable evaluation that cannot be provided by traditional metrics. Moreover, our metric emphasizes facial primary regions considering that even minor changes to the eyes, nose, and mouth significantly affect human cognition. Our face-oriented metric consistently surpasses existing general or facial image quality assessment metrics by impressive margins. We demonstrate the generalizability of the proposed strategy in various architectural designs and challenging scenarios. Interestingly, we find that our IFQA can lead to performance improvement as an objective function.