In few-shot image generation, directly training GAN models on just a handful of images faces the risk of overfitting. A popular solution is to transfer the models pretrained on large source domains to small target ones. In this work, we introduce WeditGAN, which realizes model transfer by editing the intermediate latent codes $w$ in StyleGANs with learned constant offsets ($\Delta w$), discovering and constructing target latent spaces via simply relocating the distribution of source latent spaces. The established one-to-one mapping between latent spaces can naturally prevents mode collapse and overfitting. Besides, we also propose variants of WeditGAN to further enhance the relocation process by regularizing the direction or finetuning the intensity of $\Delta w$. Experiments on a collection of widely used source/target datasets manifest the capability of WeditGAN in generating realistic and diverse images, which is simple yet highly effective in the research area of few-shot image generation.

翻译：在少样本图像生成中，直接使用少量图像训练生成对抗网络（GAN）模型面临过拟合风险。一种常见解决方案是将在大规模源域上预训练的模型迁移到小规模目标域。本文提出WeditGAN，通过利用学习到的恒定偏移量（Delta w）编辑StyleGAN中的中间潜在编码w，实现模型迁移——即通过简单重定位源潜在空间分布来发现并构建目标潜在空间。这种在潜在空间之间建立的一一映射关系能自然防止模式崩溃和过拟合。此外，我们还提出WeditGAN的变体，通过约束偏移方向或微调Delta w的强度进一步优化重定位过程。在多个广泛使用的源/目标数据集上的实验表明，WeditGAN能够生成逼真且多样化的图像，在少样本图像生成研究领域中兼具简洁性和高效性。