IFQA: Interpretable Face Quality Assessment

초록

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 discrim- inator 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 af- fect human cognition. Our face-oriented metric consistently surpasses existing general or facial image quality assess- ment metrics by impressive margins. We demonstrate the generalizability of the proposed strategy in various archi- tectural designs and challenging scenarios. Interestingly, we find that our IFQA can lead to performance improve- ment as an objective function.