文献类型：期刊文献

英文题名：GAN semantics for personalized facial beauty synthesis and enhancement

作者：Lebedeva, Irina[1];Ying, Fangli[2];Guo, Yi[3,4];Li, Taihao[1]

机构：[1]Res Inst Artificial Intelligence, Zhejiang Lab, Hangzhou, Peoples R China;[2]East China Univ Sci & Technol, Dept Comp Sci & Engn, State Key Lab Bioreactor Engn, Shanghai, Peoples R China;[3]Natl Engn Lab Big Data Distribut & Exchange Techno, Shanghai, Peoples R China;[4]Shanghai Engn Res Ctr Big Data & Internet Audience, Shanghai, Peoples R China

年份：2026

卷号：114

外文期刊名：JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION

收录：;EI(收录号：20254719573257);WOS:【SCI-EXPANDED(收录号:WOS:001626686600001)】；

基金：This research is financially supported by Research and Development Plan in Shandong Province (Grant number: 2022CXGC020206); is also supported by National Maior Scientific Instruments and Equipments Development Project of National Natural Science Foundation of China (Grant number: 32327801); is also supported by National Major Science and Technology Projects of China (Grant numbers: 2021ZD0114303); is also supported by The National Key Research and Development Program of China (Grant numbers: 2018YFC0807105); in part by the National Science and Technology Major Project of the Ministry of Science and Technology of China under Grant No. 2021ZD0114303; in part by the Key Research Project of Zhejiang Lab under Grant No. 2020KB0AC01; in part by the Open Research Project of Shanghai Key Laboratory of Brain-Machine Intelligence for Information Behavior under Grant No. 2022KFKT002.

语种：英文

外文关键词：Face synthesis; Generative adversarial networks; Facial beauty prediction; Face beautification

摘要：Generative adversarial networks (GANs) whose popularity and scope of applications continue to grow, have already demonstrated impressive results in human face image processing. Face aging, completion, attribute transfer, and synthesis are not the only examples of the successful implementation of GANs. Although, beauty enhancement and face generation with conditioning on attractiveness level are also among the applications of GANs, it has been investigated only from the universal or generic point of view, and there are no studies addressed to the personalized aspect of these issues. In this work, this gap is filled and a generative framework that synthesizes a realistic human face that is based on an individual's beauty preferences is introduced. To this end, StyleGAN's properties and the capacities of semantic face manipulation in its latent space are studied and utilized. Beyond the face generation, the proposed framework is able to enhance a beauty level on a real face according to personal beauty preferences. Extensive experiments are conducted on two publicly available facial beauty datasets with different properties in terms of images and raters, SCUT-FBP5500 and multi-ethnic MEBeauty. The quantitative evaluations demonstrate the effectiveness of the proposed framework and its advantages compared to the state-of-the-art, while the qualitative evaluations also reveal and illustrate interesting social and cultural patterns in personal beauty preferences.