Going the extra mile in face image quality assessment: a novel database and model

Su, Shaolin, Lin, Hanhe, Hosu, Vlad, Wiedemann, Oliver, Sun, Jinqiu, Zhu, Yu, Liu, Hantao ORCID: https://orcid.org/0000-0003-4544-3481, Zhang, Yanning and Saupe, Dietmar 2023. Going the extra mile in face image quality assessment: a novel database and model. IEEE Transactions on Multimedia 10.1109/TMM.2023.3301276

Preview

PDF - Accepted Post-Print Version Download (7MB) | Preview

Abstract

An accurate computational model for image quality assessment (IQA) benefits many vision applications, such as image filtering, image processing, and image generation. Although the study of face images is an important subfield in computer vision research, the lack of face IQA data and models limits the precision of current IQA metrics on face image processing tasks such as face superresolution, face enhancement, and face editing. To narrow this gap, in this paper, we first introduce the largest annotated IQA database developed to date, which contains 20,000 human faces – an order of magnitude larger than all existing rated datasets of faces – of diverse individuals in highly varied circumstances. Based on the database, we further propose a novel deep learning model to accurately predict face image quality, which, for the first time, explores the use of generative priors for IQA. By taking advantage of rich statistics encoded in well pretrained off-the-shelf generative models, we obtain generative prior information and use it as latent references to facilitate blind IQA. The experimental results demonstrate both the value of the proposed dataset for face IQA and the superior performance of the proposed model.

Item Type:	Article
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	1520-9210
Date of First Compliant Deposit:	8 September 2023
Date of Acceptance:	21 July 2023
Last Modified:	16 Nov 2023 21:45
URI:	https://orca.cardiff.ac.uk/id/eprint/162338

Actions (repository staff only)

Edit Item