IFQA: 可解释人脸质量评估
IFQA: Interpretable Face Quality Assessment
AI总结：
针对现有通用人脸质量评估指标不适配人脸特征、人工评估成本高的问题，提出基于对抗框架的可解释人脸质量评估指标IFQA，聚焦人脸关键区域，性能优于现有指标且可作为目标函数提升模型效果。
摘要：
现有的人脸修复模型依赖通用评估指标，这类指标未考虑人脸区域的特征。因此近期研究通过人类受试者实验评估方法，该方式无法规模化且耗费大量精力。本文提出一种新颖的以人脸为中心的指标，该指标基于对抗框架：生成器模拟人脸修复过程，判别器评估图像质量。具体而言，我们的逐像素判别器可实现传统指标无法提供的可解释评估。此外，考虑到眼睛、鼻子和嘴巴的微小变化都会显著影响人类认知，我们的指标会重点关注人脸主要区域。我们的面向人脸的指标始终以显著优势超越现有的通用或人脸图像质量评估指标。我们验证了所提策略在多种架构设计和挑战性场景下的泛化性。有趣的是，我们发现IFQA作为目标函数使用时还能带来性能提升。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
