用扩散模型的得分函数构建黎曼几何，实现更真实的图像插值。
Image Interpolation with Score-based Riemannian Metrics of Diffusion Models
- 基于得分函数定义数据空间的黎曼度量，构建几何感知插值路径。
- 在MNIST和Stable Diffusion上，插值结果更真实、更少噪声、更贴合提示。
- 适合需要高质量图像生成与编辑的科研与设计场景。
扩散模型通过隐式学习数据流形在内容生成方面表现出色，但缺乏有效利用该流形的实用方法——与其他具备潜在空间的深度生成模型不同。本文提出一种新框架，将预训练扩散模型的数据空间视为黎曼流形，并基于得分函数构建其度量。在MNIST与Stable Diffusion上的实验表明，这种几何感知方法生成的图像插值更真实、噪声更少、对提示的忠实度更高，展现出在内容生成与编辑中的潜力。
原文摘要 · Abstract (English)
Diffusion models excel in content generation by implicitly learning the data manifold, yet they lack a practical method to leverage this manifold - unlike other deep generative models equipped with latent spaces. This paper introduces a novel framework that treats the data space of pre-trained diffusion models as a Riemannian manifold, with a metric derived from the score function. Experiments with MNIST and Stable Diffusion show that this geometry-aware approach yields image interpolations that are more realistic, less noisy, and more faithful to prompts than existing methods, demonstrating its potential for improved content generation and editing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。