扩散模型解纠缠潜在空间的等距表示学习
Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
AI总结：
针对扩散模型潜在空间纠缠和映射畸变问题，提出等距扩散方法，通过几何正则化器学习解纠缠潜在空间，实现更平滑插值、更精确反演和更精细属性控制，实验验证有效。
摘要：
尽管扩散模型在生成建模领域取得了巨大成功和潜力，但其潜在空间在很大程度上仍未得到探索。事实上，现有扩散模型的潜在空间是纠缠的，其潜在空间到图像空间的映射存在畸变。为了解决这一问题，我们提出了等距扩散（Isometric Diffusion），通过为扩散模型配备几何正则化器，引导模型学习训练数据流形的几何上合理的潜在空间。该方法使扩散模型能够学习更解纠缠的潜在空间，从而实现更平滑的插值、更精确的反演以及直接在潜在空间中对属性进行更精细的控制。我们包含图像插值、图像反演和线性编辑的大量实验证明了我们方法的有效性。
英文摘要：
The latent space of diffusion model mostly still remains unexplored, despite its great success and potential in the field of generative modeling. In fact, the latent space of existing diffusion models are entangled, with a distorted mapping from its latent space to image space. To tackle this problem, we present Isometric Diffusion, equipping a diffusion model with a geometric regularizer to guide the model to learn a geometrically sound latent space of the training data manifold. This approach allows diffusion models to learn a more disentangled latent space, which enables smoother interpolation, more accurate inversion, and more precise control over attributes directly in the latent space. Our extensive experiments consisting of image interpolations, image inversions, and linear editing show the effectiveness of our method.
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。
