文献类型：期刊文献

英文题名：Identity-Preserving Facial Aesthetic Enhancement via Hierarchical Prompt Learning and Pivotal Tuning

作者：Ying, Fangli[1]; Zhang, Zhihong[2]; Zhou, Liting[3]; Gurrin, Cathal[3]; Wang, Jinhai[4]

机构：[1] Department of Computer Science, East China University of Science and Technology, Shanghai, China; [2] School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China; [3] School of Computing, Dublin City University, Dublin, Ireland; [4] Xinfei Yuyuan [Shanghai] Digital Technology Co., Ltd., Shanghai, China

年份：2025

起止页码：10690

外文期刊名：MM 2025 - Proceedings of the 33rd ACM International Conference on Multimedia, Co-Located with MM 2025

收录：EI(收录号：20255019680505)

语种：英文

外文关键词：Human engineering - Latent semantic analysis - Tuning

摘要：The demand for identity-preserving Facial Aesthetic Enhancement (FAE) has surged in social media and digital entertainment. However, existing methods based on deep generative models encounter difficulties in striking a balance between fine-grained detail enhancement and preserving the unique identities of individuals from diverse ethnic and gender backgrounds. To tackle this issue, this paper proposes a novel tuning-based framework that integrates prototype-based hierarchical prompt learning within a CLIP model and a StyleGAN-based inversion model. Our approach first adapts a pre-trained StyleGAN to the input face via pivotal tuning, optimizing around pivotal latent codes to minimize reconstruction distortion while retaining editability. Then, a prototype-based hierarchical prompt learning module is designed for learning multigrained facial features to achieve comprehensive and fine-grained facial descriptions for FAE. Specifically, we propose a prototypical similarity measure based on a multi-ethnic dataset to select geometrically similar faces with high aesthetic scores as reference faces. This selection is guided by ArcFace regularization within categorized gender and ethnic groups to minimize identity loss. Additionally, we design a novel aesthetic attribute selection algorithm to generate generic fine-grained aesthetic attributes from these reference faces for detailed facial descriptions. These components work synergistically through dynamic weight modulation, prioritizing features with high aesthetic contributions (such as enhancing lip fullness) while ensuring semantic consistency through CLIP-driven optimization for pivotal latent codes. Extensive experiments demonstrate that our method outperforms state-of-the-art techniques in both aesthetic quality and identity preservation, especially for out-of-domain faces. ? 2025 ACM.