期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 25, 期 -, 页码 4213-4224出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2022.3172548
关键词
Faces; Modulation; Task analysis; Tensors; Training; Generators; Lighting; Fine-grained; face editing; generative adversarial networks
This paper proposes a novel method called Personalized Spatial-aware Affine Modulation (PSAM) to address the problem of fine-grained face editing. The method utilizes personalized and spatial-aware modulation of intermediate features to modify face attributes according to users' preference.
Fine-grained face editing, as a special case of image translation task, aims at modifying face attributes according to users' preference. Although generative adversarial networks (GANs) have achieved great success in general image translation tasks, these models cannot be directly applied in the face editing problem. Ideal face editing is challenging as it has two special requirements - personalization and spatial-awareness. To address these issues, we propose a novel Personalized Spatial-aware Affine Modulation (PSAM) method based on a general GAN structure. The key idea is to modulate the intermediate features in a personalized and spatial-aware manner, which corresponds to the face editing procedure. Specifically, for personalization, we adopt both the face image and the desired attribute as input to generate the modulation tensors. For spatial-aware, we set these tensors to be of the same size as the input image, allowing pixel-wise modulation. Extensive experiments in four fine-grained face editing tasks, i.e., makeup, expression, illumination and aging, demonstrate the effectiveness of the proposed PSAM method. The synthesis results of PSAM can be further boosted by a new transferable training strategy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据