论文标题
具有生成对抗网络的属性意识到面部生成
Attributes Aware Face Generation with Generative Adversarial Networks
论文作者
论文摘要
最近的研究表明，面部图像世代取得了巨大的成功。但是，大多数现有方法仅从随机噪声中生成面部图像，并且无法根据特定属性生成面部图像。在本文中，我们关注属性的面部合成问题，该问题旨在生成具有与给定属性相对应的特定特征的面部。为此，我们提出了一种新颖的属性，具有称为Afgan的生成对抗网络的意识到的面部图像生成器方法。具体而言，我们首先提出了一个两路的嵌入层和自我发项机制，以将二进制属性向量转换为丰富的属性特征。然后，三个堆叠发电机生成$ 64 \ times 64 $，$ 128 \ times 128 $和$ 256 \ times 256 $分别通过将属性功能作为输入来分别。另外，提出了图像属性匹配损失，以增强生成的图像和输入属性之间的相关性。关于Celeba的广泛实验表明，从定性和定量评估方面，我们的Afgan具有优势。
Recent studies have shown remarkable success in face image generations. However, most of the existing methods only generate face images from random noise, and cannot generate face images according to the specific attributes. In this paper, we focus on the problem of face synthesis from attributes, which aims at generating faces with specific characteristics corresponding to the given attributes. To this end, we propose a novel attributes aware face image generator method with generative adversarial networks called AFGAN. Specifically, we firstly propose a two-path embedding layer and self-attention mechanism to convert binary attribute vector to rich attribute features. Then three stacked generators generate $64 \times 64$, $128 \times 128$ and $256 \times 256$ resolution face images respectively by taking the attribute features as input. In addition, an image-attribute matching loss is proposed to enhance the correlation between the generated images and input attributes. Extensive experiments on CelebA demonstrate the superiority of our AFGAN in terms of both qualitative and quantitative evaluations.
