arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.11751cs.CV
收藏

基于分数的扩散模型作为逆成像的原理性先验

Score-Based Diffusion Models as Principled Priors for Inverse Imaging

California Institute of Technology(加州理工学院);Google Research(谷歌研究院)

Berthy T. Feng, Jamie Smith, Michael Rubinstein, Huiwen Chang, Katherine L. Bouman, William T. Freeman

AI总结:

本文提出将基于分数的扩散模型作为原理性图像先验,通过实证验证其概率函数并用于变分推断,在去噪、去模糊和干涉成像中实现高质量重建。

摘要:

先验对于从噪声和/或不完整测量中重建图像至关重要。先验的选择决定了恢复图像的质量和不确定性。我们提出将基于分数的扩散模型转化为原理性图像先验(“基于分数的先验”),用于分析给定测量下图像的后验。此前,概率先验仅限于手工设计的正则化器和简单分布。在本工作中,我们实证验证了基于分数的扩散模型的理论证明概率函数。我们展示了如何通过使用该概率函数进行变分推断来从所得后验中采样。我们的结果,包括去噪、去模糊和干涉成像实验,表明基于分数的先验能够借助复杂的数据驱动图像先验实现原理性推断。

英文摘要:

Priors are essential for reconstructing images from noisy and/or incomplete measurements. The choice of the prior determines both the quality and uncertainty of recovered images. We propose turning score-based diffusion models into principled image priors ("score-based priors") for analyzing a posterior of images given measurements. Previously, probabilistic priors were limited to handcrafted regularizers and simple distributions. In this work, we empirically validate the theoretically-proven probability function of a score-based diffusion model. We show how to sample from resulting posteriors by using this probability function for variational inference. Our results, including experiments on denoising, deblurring, and interferometric imaging, suggest that score-based priors enable principled inference with a sophisticated, data-driven image prior.

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。

↑