将扩散模型转化为几步采样的后验采样器，兼顾精度与灵活性。
Learning few-step posterior samplers by unfolding and distillation of diffusion models
- 通过深度展开马尔可夫链蒙特卡洛算法，构建少步采样器。
- 在多个任务上达到顶尖精度，推理速度显著提升。
- 适合需要快速适应不同成像模型的场景。
扩散模型（DMs）已成为贝叶斯计算成像中的强大图像先验。现有两类主要策略：即插即用方法无需训练但依赖近似；专用条件扩散模型通过监督训练实现更高精度与更快推理。本文提出一种新框架，结合深度展开与模型蒸馏，将扩散模型图像先验转化为少步条件后验采样器。核心创新是首次将深度展开应用于蒙特卡洛采样方案——具体为近期提出的LATINO Langevin采样器（Spagnoletti et al., 2025）。通过大量实验与最先进方法对比，所提展开并蒸馏的采样器在精度和计算效率上表现优异，同时保留了在推理时适应不同前向模型变化的灵活性。
原文摘要 · Abstract (English)
Diffusion models (DMs) have emerged as powerful image priors in Bayesian computational imaging. Two primary strategies have been proposed for leveraging DMs in this context: Plug-and-Play methods, which are zero-shot and highly flexible but rely on approximations; and specialized conditional DMs, which achieve higher accuracy and faster inference for specific tasks through supervised training. In this work, we introduce a novel framework that integrates deep unfolding and model distillation to transform a DM image prior into a few-step conditional model for posterior sampling. A central innovation of our approach is the unfolding of a Markov chain Monte Carlo (MCMC) algorithm - specifically, the recently proposed LATINO Langevin sampler (Spagnoletti et al., 2025) - representing the first known instance of deep unfolding applied to a Monte Carlo sampling scheme. We demonstrate our proposed unfolded and distilled samplers through extensive experiments and comparisons with the state of the art, where they achieve excellent accuracy and computational efficiency, while retaining the flexibility to adapt to variations in the forward model at inference time.
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。