浙江大学学报（理学版）2026，Vol.53Issue(2)：191-199,9.DOI:10.3785/j.issn.1008-9497.25126
DeltaAge:一种高保真人脸年龄编辑网络
DeltaAge:A high-fidelity face age editing network
摘要
Abstract
Current mainstream facial age editing methods predominantly rely on generative adversarial networks(GANs)or diffusion models,which typically necessitate training on paired age-annotated datasets.These approaches are often constrained by suboptimal generation quality and the ineffective decoupling of age-related attributes from other facial features.To address these limitations,this paper proposes a diffusion autoencoder-based approach for facial age editing.The method employs a dual-branch architecture to effectively disentangle identity-specific and age-related attributes,coupled with a novel diversity loss to enhance the expressiveness of synthesized aging patterns.Experimental results on the CelebA-HQ dataset demonstrate that DeltaAge achieves superior performance in term of the blur index,robustly validating its high-fidelity editing capabilities.关键词
高保真/人脸年龄编辑/扩散模型/图像编辑Key words
high-fidelity/facial age editing/diffusion models/image editing分类
信息技术与安全科学引用本文复制引用
梁汉亿,李辉,盖孟,王少荣..DeltaAge:一种高保真人脸年龄编辑网络[J].浙江大学学报（理学版）,2026,53(2):191-199,9.基金项目
南方海洋科学与工程广东省实验室(珠海)资助项目(SML2021SP10). （珠海）
