This work presents an easy-to-use regularizer for GAN training, which helps explicitly link some axes of the latent space to a set of pixels in the synthesized image. Establishing such a connection facilitates a more convenient local control of GAN generation, where users can alter the image content only within a spatial area simply by partially resampling the latent code. Experimental results confirm four appealing properties of our regularizer, which we call LinkGAN. (1) The latent-pixel linkage is applicable to either a fixed region (\textit{i.e.}, same for all instances) or a particular semantic category (i.e., varying across instances), like the sky. (2) Two or multiple regions can be independently linked to different latent axes, which further supports joint control. (3) Our regularizer can improve the spatial controllability of both 2D and 3D-aware GAN models, barely sacrificing the synthesis performance. (4) The models trained with our regularizer are compatible with GAN inversion techniques and maintain editability on real images.

翻译：本文提出一种易于使用的生成对抗网络（GAN）训练正则化器，能够显式地将潜空间的某些轴向与合成图像中的像素集相关联。建立这种连接有助于实现更便捷的局部GAN生成控制——用户只需对潜编码进行部分重采样，即可在空间区域内单独修改图像内容。实验结果验证了我们称为LinkGAN的正则化器具有四个引人注目的特性：（1）潜变量-像素链接既可应用于固定区域（即对所有实例相同），也可应用于特定语义类别（即在不同实例间变化），例如天空；（2）两个或多个区域可独立链接至不同潜变量轴向，从而支持联合控制；（3）我们的正则化器能在几乎不牺牲合成性能的前提下，提升二维和三维感知GAN模型的空间可控性；（4）经该正则化器训练的模型与GAN逆变换技术兼容，且能保持对真实图像的可编辑性。