BriefGPT.xyz
Jul, 2023
通过潜在扩散模型的后验抽样可证明解决线性反问题
Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models
HTML
PDF
Litu Rout, Negin Raoof, Giannis Daras, Constantine Caramanis, Alexandros G. Dimakis...
TL;DR
我们提出了第一个框架，利用预先训练好的潜在扩散模型来解决线性反问题。在理论和实验分析中，我们都展现出在各种问题中都优于先前提出的后验采样算法，包括随机修补、块修补、去噪、去模糊处理、去除条纹和超分辨率。
Abstract
We present the first framework to solve
linear inverse problems
leveraging pre-trained
latent diffusion models
. Previously proposed algorithms (such as DPS and DDRM) only apply to pixel-space diffusion models. We
→