IFQA: Interpretable Face Quality Assessment

    Byungho Jo1, Donghyeon Cho2, In Kyu Park1, and Sungeun Hong1

     1Inha University               2Chungnam National University

WACV 2023


Which of ‘Image A’ or ‘Image B’ is closer to the given reference image or looks high-quality? General full-reference metrics (e.g. PSNR/SSIM), no-reference metrics (e.g. NIQE, BRISQUE, PI), and FIQA methods are inconsistent with human judgment. LPIPS agrees with human judgment but cannot be applied to the blind face restoration scenario. Our IFQA is consistent with human judgment and can provide interpretability maps where the brighter the area, the higher the quality.

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. The code and models areavailable at https://github.com/VCLLab/IFQA.


Our Framework

Given HQ images, we obtain LQ images via BFR formulation. The generator (G) mimics face restoration models, while the discriminator (D) is used to evaluate image quality by determining high-quality regions as ‘real’ and low-quality or restored regions as ‘fake’. Through its U-Net architecture, the discriminator is able to evaluate the image pixel-by-pixel. FPRS allows the proposed metric to give more weight to facial primary regions that have a significant impact on human visual perception.


Quantitative Results

Comparison to No-Reference IQA Metrics [1-7]

Qualitative Results

FFHQ images [8]

In the wild face images [9]

BibTex

@InProceedings{Jo_2023_WACV,

author = {Byungho, Jo and Cho, Donghyeon and Park, In Kyu and Hong, Sungeun},

title = {IFQA: Interpretable Face Quality Assessment},

booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},

month = {January},

year = {2023},

pages = {-}

}

References