生成场：通过倒置感受野揭示StyleGAN的分层特征控制
Generative Fields: Uncovering Hierarchical Feature Control for StyleGAN via Inverted Receptive Fields
AI总结：
本文提出生成场概念，受CNN感受野启发，利用通道级风格潜空间S实现StyleGAN分层特征的解耦控制，提出新的图像编辑流程。
摘要：
StyleGAN已经证明了生成对抗网络（GAN）能够从随机噪声中合成逼真的虚构人物面部图像。基于GAN的图像生成的一个局限性在于，由于低维潜空间的强纠缠性，难以控制生成图像的特征。以往旨在通过图像或文本提示控制StyleGAN的工作，在W潜空间中进行调制采样，该空间比Z潜空间更具表达能力。然而，W空间仍然具有受限的表达能力，因为它不直接控制特征合成；此外，W空间中的特征嵌入需要预训练过程来重建风格信号，限制了其应用。本文受卷积神经网络（CNN）感受野的启发，引入了“生成场”的概念来解释StyleGAN中的分层特征合成。此外，我们提出了一种新的StyleGAN图像编辑流程，利用生成场理论和通道级风格潜空间S，利用CNN的内在结构特征，在合成时实现对特征合成的解耦控制。
英文摘要：
StyleGAN has demonstrated the ability of GANs to synthesize highly-realistic faces of imaginary people from random noise. One limitation of GAN-based image generation is the difficulty of controlling the features of the generated image, due to the strong entanglement of the low-dimensional latent space. Previous work that aimed to control StyleGAN with image or text prompts modulated sampling in W latent space, which is more expressive than Z latent space. However, W space still has restricted expressivity since it does not control the feature synthesis directly; also the feature embedding in W space requires a pre-training process to reconstruct the style signal, limiting its application. This paper introduces the concept of "generative fields" to explain the hierarchical feature synthesis in StyleGAN, inspired by the receptive fields of convolution neural networks (CNNs). Additionally, we propose a new image editing pipeline for StyleGAN using generative field theory and the channel-wise style latent space S, utilizing the intrinsic structural feature of CNNs to achieve disentangled control of feature synthesis at synthesis time.
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。
