IFQA: Interpretable Face Quality Assessment
This addresses the need for scalable and interpretable quality assessment in face restoration, which is important for researchers and practitioners in computer vision, though it is incremental as it builds on adversarial frameworks.
The paper tackles the problem of assessing face restoration quality by proposing IFQA, an interpretable face-centric metric that surpasses existing general or facial image quality assessment metrics by impressive margins.
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.