Generative Adversarial Networks (GANs) have been widely applied in modeling
diverse image distributions. However, despite its impressive applications, the
structure of the latent space in GANs largely remains as a black-box, leaving
its controllable generation an open problem, especial
我们提出了一个具有明确控制 GAN 生成的图像的框架,借助于对抗性训练(GANs)、明确控制的潜在空间以及对人类的符号解释模型进行了对生成图像的控制,可扩展到人类脸谱以外的领域,实现了身份、年龄、姿态、表情、头发色彩和光照方面的控制,并且在画像和狗图像生成的领域中都展示了控制能力,同时表现出优良的定量和定性性能。