BriefGPT.xyz
Apr, 2023
基于分数的扩散模型作为反向成像的原则先验
Score-Based Diffusion Models as Principled Priors for Inverse Imaging
HTML
PDF
Berthy T. Feng, Jamie Smith, Michael Rubinstein, Huiwen Chang, Katherine L. Bouman...
TL;DR
本文提出了将基于分数的扩散模型转化为原则性先验（``基于分数的先验'）来分析给定测量的后验图像的方法。实验结果表明，基于分数的先验使得数据驱动图像先验的归纳推理变得更加精细。
Abstract
It is important in
computational imaging
to understand the uncertainty of images reconstructed from imperfect measurements. We propose turning
score-based diffusion models
into principled priors (``score-based pr
→