通过微调GAN编码器改进生成对抗网络反演
Improving generative adversarial network inversion via fine-tuning GAN encoders
AI总结：
针对现有GAN反演方法性能有限、泛化性差的问题，提出一种自监督预训练与微调GAN编码器的方法，通过自适应模块适配多架构，实现主流GAN上更优的高质量图像重建。
摘要：
生成对抗网络（GANs）能够合成高质量（HQ）图像，GAN反演是一种探索如何将给定图像反向映射回潜在空间的技术。现有方法虽可用于StyleGAN反演，但性能有限，且无法推广到不同的GAN。为解决这些问题，我们提出了一种自监督方法来预训练和微调GAN编码器。首先，我们设计了一个自适应模块，以适配不同的编码器架构，用于反演多种GAN。接着，我们使用合成图像预训练GAN编码器，并通过裁剪图像来突出局部区域。最后，我们对预训练的GAN编码器进行微调，以用于真实图像的反演。与当前最优方法相比，我们的方法在主流GAN上取得了更优的高质量图像重建效果。我们的代码和预训练模型可在以下链接获取：https://github.com/disanda/Deep-GAN-Encoders。
英文摘要：
Generative adversarial networks (GANs) can synthesize high-quality (HQ) images, and GAN inversion is a technique that discovers how to invert given images back to latent space. While existing methods perform on StyleGAN inversion, they have limited performance and are not generalized to different GANs. To address these issues, we proposed a self-supervised method to pre-train and fine-tune GAN encoders. First, we designed an adaptive block to fit different encoder architectures for inverting diverse GANs. Then we pre-train GAN encoders using synthesized images and emphasize local regions through cropping images. Finally, we fine-tune the pre-trained GAN encoder for inverting real images. Compared with state-of-the-art methods, our method achieved better results that reconstructed high-quality images on mainstream GANs. Our code and pre-trained models are available at: https://github.com/disanda/Deep-GAN-Encoders.
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。
