Generative Adversarial Networks (GANs) convergence in a high-resolution setting with a computational constrain of GPU memory capacity (from 12GB to 24 GB) has been beset with difficulty due to the known lack of convergence rate stability. In order to boost network convergence of DCGAN (Deep Convolutional Generative Adversarial Networks) and achieve good-looking high-resolution results we propose a new layered network structure, HR-DCGAN, that incorporates current state-of-the-art techniques for this effect. A novel dataset, CZ Faces (CZF), containing human faces from different ethnical groups in a wide variety of illumination conditions and image resolutions is introduced. We conduct extensive experiments on CelebA and CZF.

提出了一种新的分层网络 HDCGAN，结合当前最先进的技术，用于提高 DCGAN 的网络收敛性能，从而获得良好的高分辨率结果，并引入了一个新的无偏数据集 Curtó & Zarza，该数据集包含不同 ethnical groups 中的人脸，在各种光照条件和图像分辨率下， Curtó 通过 HDCGAN 的合成图像进行增强，因此是第一个被 GAN 增强的人脸数据集，性能达到了当前 CelebA 合成图像生成的最高水平，实现了 MS-SSIM 为 0.1978 和 FRÉCHET Inception 距离为 8.44。

高分辨率深度卷积生成对抗网络