面向忠实重建与可编辑性的域内 GAN 反演
In-Domain GAN Inversion for Faithful Reconstruction and Editability
AI总结：
本文提出域内 GAN 反演，通过域引导编码器与域正则化优化器约束潜码，在保证真实图像忠实重建的同时提升语义可编辑性。
摘要：
生成对抗网络（GAN）通过将随机采样的潜码映射到高保真合成图像，显著推动了图像合成的发展。然而，将训练良好的 GAN 应用于真实图像编辑仍然具有挑战性。一种常见解决方案是找到一个能够充分恢复待编辑输入图像的近似潜码，这也被称为 GAN 反演。为了反演 GAN 模型，以往工作通常关注在像素级重建目标图像，但很少有研究探讨反演结果能否在语义层面很好地支持操控。本工作通过提出域内 GAN 反演来填补这一空白，该方法由域引导编码器和域正则化优化器组成，用于在预训练 GAN 模型的原生潜空间中正则化反演代码。通过这种方式，我们能够充分复用 GAN 学到的知识进行图像重建，在无需任何重新训练的情况下促进广泛的编辑应用。我们进一步全面分析了编码器结构、反演起始点以及反演参数空间的影响，并观察到重建质量与编辑属性之间的权衡。这种权衡揭示了 GAN 模型如何利用学习到的潜分布中编码的各种语义来表示图像。代码、模型和演示可在项目页面获取：https://genforce.github.io/idinvert/。
英文摘要：
Generative Adversarial Networks (GANs) have significantly advanced image synthesis through mapping randomly sampled latent codes to high-fidelity synthesized images. However, applying well-trained GANs to real image editing remains challenging. A common solution is to find an approximate latent code that can adequately recover the input image to edit, which is also known as GAN inversion. To invert a GAN model, prior works typically focus on reconstructing the target image at the pixel level, yet few studies are conducted on whether the inverted result can well support manipulation at the semantic level. This work fills in this gap by proposing in-domain GAN inversion, which consists of a domain-guided encoder and a domain-regularized optimizer, to regularize the inverted code in the native latent space of the pre-trained GAN model. In this way, we manage to sufficiently reuse the knowledge learned by GANs for image reconstruction, facilitating a wide range of editing applications without any retraining. We further make comprehensive analyses on the effects of the encoder structure, the starting inversion point, as well as the inversion parameter space, and observe the trade-off between the reconstruction quality and the editing property. Such a trade-off sheds light on how a GAN model represents an image with various semantics encoded in the learned latent distribution. Code, models, and demo are available at the project page: https://genforce.github.io/idinvert/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
