通过最短路径优化去噪扩散模型，提升生成速度与质量。
Optimizing for the Shortest Path in Denoising Diffusion Model
- 将去噪过程建模为最短路径问题，优化初始残差传播。
- 在多个基准上显著减少采样步骤，同时提升图像保真度。
- 适合需要快速生成的交互式应用，如实时图像编辑。
本研究提出一种基于最短路径建模的新型去噪扩散模型，通过优化残差传播提升去噪效率与生成质量。受去噪扩散隐式模型（DDIM）和图论启发，所提出的短路径扩散模型（ShortDF）将去噪过程视为最小化重构误差的最短路径问题。通过优化初始残差，提升了反向扩散过程的效率与生成样本的质量。在多个标准基准上的大量实验表明，相较于先前方法，ShortDF显著减少了扩散时间（或步骤数），同时增强了生成样本的视觉保真度。本文工作有望推动基于扩散的交互式应用发展，并为快速数据生成奠定基础。代码已开源：https://github.com/UnicomAI/ShortDF。
原文摘要 · Abstract (English)
In this research, we propose a novel denoising diffusion model based on shortest-path modeling that optimizes residual propagation to enhance both denoising efficiency and quality. Drawing on Denoising Diffusion Implicit Models (DDIM) and insights from graph theory, our model, termed the Shortest Path Diffusion Model (ShortDF), treats the denoising process as a shortest-path problem aimed at minimizing reconstruction error. By optimizing the initial residuals, we improve the efficiency of the reverse diffusion process and the quality of the generated samples. Extensive experiments on multiple standard benchmarks demonstrate that ShortDF significantly reduces diffusion time (or steps) while enhancing the visual fidelity of generated samples compared to prior arts. This work, we suppose, paves the way for interactive diffusion-based applications and establishes a foundation for rapid data generation. Code is available at https://github.com/UnicomAI/ShortDF.
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。