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 |