A3GAN: An Attribute-Aware Attentive Generative Adversarial Network for Face Aging
A3GAN: An Attribute-Aware Attentive Generative Adversarial Network for Face Aging
复制标题
A3GAN：用于人脸老化的属性感知注意力生成对抗网络
DOI：
10.1109/tifs.2021.3065499
复制
发表时间：
2021-01-01
影响因子：
6.8
通讯作者：
Tan, Tieniu
中科院分区：
文献类型：
--
作者：
Liu, Yunfan;Li, Qi;Tan, Tieniu
近年来，面部衰老受到了重要的研究关注。虽然随着生成对抗网络（GAN）在合成真实图像方面的成功取得了很大进展，但大多数现有的基于GAN的人脸老化方法都存在两个主要问题：1）由于对输入人脸的先验知识考虑不足，导致高级语义信息的不自然变化，以及2）低级别图像内容的失真（例如，与年龄无关的区域的修改）。在这篇文章中，我们介绍了A（3）GAN，一个属性感知的注意人脸老化模型来解决上述问题。人脸属性向量被视为条件信息，并嵌入到生成器和SVM，鼓励合成的脸是忠实于相应的输入属性。为了提高生成结果的视觉保真度，我们利用注意力机制来限制对年龄相关区域的修改并保留图像细节。与以前的作品与注意模块，我们引入了面部解析图，以帮助生成器区分感兴趣的图像区域，并抑制其他地方的注意激活。此外，小波包变换被用来捕捉纹理特征在多个尺度上的频率空间。大量的实验结果表明，我们的模型在合成照片般逼真的老化人脸图像和流行的数据集上实现最先进的性能的有效性。
Face aging has received significant research attention in recent years. Although great progress has been achieved with the success of Generative Adversarial Networks (GANs) in synthesizing realistic images, most existing GAN-based face aging methods have two main problems: 1) unnatural changes of high-level semantic information due to the insufficient consideration of prior knowledge of input faces, and 2) distortions of low-level image content (e.g. modifications in age-irrelevant regions). In this article, we introduce A(3)GAN, an Attribute-Aware Attentive face aging model to address the above issues. Facial attribute vectors are regarded as the conditional information and embedded into both the generator and discriminator, encouraging synthesized faces to be faithful to attributes of corresponding inputs. To improve the visual fidelity of generation results, we leverage the attention mechanism to restrict modifications to age-related areas and preserve image details. Unlike previous works with attention modules, we introduce face parsing maps to help the generator distinguish image regions of interest and suppress attention activation elsewhere. Moreover, the wavelet packet transform is employed to capture textural features at multiple scales in the frequency space. Extensive experimental results demonstrate the effectiveness of our model in synthesizing photo-realistic aged face images and achieving state-of-the-art performance on popular datasets.