DiffuseGAE：基于解耦表示的可控且高保真图像编辑
DiffuseGAE: Controllable and High-fidelity Image Manipulation from Disentangled Representation
AI总结：
本文提出 DiffuseGAE，通过 Group-supervised AutoEncoder 和属性交换训练增强 Diff-AE 的潜码解耦，实现通用、可控、高保真的多属性图像编辑，并降低计算成本。
摘要：
扩散概率模型（DPM）已在文本到图像生成和图像修复等多种图像合成任务上展现出显著成果。然而，与 VAE 和 GAN 等其他生成方法相比，DPM 缺少低维、可解释且解耦良好的潜码。最近，扩散自编码器（Diff-AE）被提出，用于通过自编码探索 DPM 在表示学习方面的潜力。Diff-AE 提供了一个可访问的潜空间，并表现出显著的可解释性，使我们能够基于该空间中的潜码操控图像属性。然而，以往工作并不通用，因为它们只处理少数有限的属性。为进一步探索 Diff-AE 的潜空间并实现通用编辑流程，我们为 Diff-AE 提出了一个名为 Group-supervised AutoEncoder（简称 GAE）的模块，以在潜码上实现更好的解耦。我们提出的 GAE 通过属性交换策略进行训练，从而基于示例获得用于多属性图像操控的潜码。我们通过实验证明，该方法能够实现多属性操控，并取得令人信服的样本质量和属性对齐效果，同时与用于表示解耦的基于像素的方法相比，显著降低了计算需求。代码即将发布。
英文摘要：
Diffusion probabilistic models (DPMs) have shown remarkable results on various image synthesis tasks such as text-to-image generation and image inpainting. However, compared to other generative methods like VAEs and GANs, DPMs lack a low-dimensional, interpretable, and well-decoupled latent code. Recently, diffusion autoencoders (Diff-AE) were proposed to explore the potential of DPMs for representation learning via autoencoding. Diff-AE provides an accessible latent space that exhibits remarkable interpretability, allowing us to manipulate image attributes based on latent codes from the space. However, previous works are not generic as they only operated on a few limited attributes. To further explore the latent space of Diff-AE and achieve a generic editing pipeline, we proposed a module called Group-supervised AutoEncoder(dubbed GAE) for Diff-AE to achieve better disentanglement on the latent code. Our proposed GAE has trained via an attribute-swap strategy to acquire the latent codes for multi-attribute image manipulation based on examples. We empirically demonstrate that our method enables multiple-attributes manipulation and achieves convincing sample quality and attribute alignments, while significantly reducing computational requirements compared to pixel-based approaches for representational decoupling. Code will be released soon.
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。
