论文标题
基于扩散模型的后验采样
Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems
论文作者
论文摘要
随着扩散模型和基于流量的生成模型的快速发展，通过生成模型解决了解决嘈杂的线性反问题（例如，超分辨率，去蓝色，去核，颜色等）的兴趣激增。但是，尽管已经实现了显着的重建性能，但它们的推理时间通常太慢了，因为它们大多数依赖于开创性扩散后采样（DPS）框架，因此需要近似于棘手的梯度分数，需要通过背部传播来进行时地累积的梯度计算。为了解决这个问题，本文通过提出对可能性得分的简单封闭形式近似来提供快速有效的解决方案。对于扩散和基于流动的模型，对各种嘈杂的线性反问题进行了广泛的实验，例如嘈杂的超分辨率，变性，去蓝色和着色。在所有这些任务中，我们的方法（即DMP）表现出高度竞争性甚至更好的重建性能，同时比所有基线方法都要快得多。
With the rapid development of diffusion models and flow-based generative models, there has been a surge of interests in solving noisy linear inverse problems, e.g., super-resolution, deblurring, denoising, colorization, etc, with generative models. However, while remarkable reconstruction performances have been achieved, their inference time is typically too slow since most of them rely on the seminal diffusion posterior sampling (DPS) framework and thus to approximate the intractable likelihood score, time-consuming gradient calculation through back-propagation is needed. To address this issue, this paper provides a fast and effective solution by proposing a simple closed-form approximation to the likelihood score. For both diffusion and flow-based models, extensive experiments are conducted on various noisy linear inverse problems such as noisy super-resolution, denoising, deblurring, and colorization. In all these tasks, our method (namely DMPS) demonstrates highly competitive or even better reconstruction performances while being significantly faster than all the baseline methods.
