BriefGPT.xyz
Aug, 2024
基于粒子滤波的潜在扩散逆问题解决方案
Particle-Filtering-based Latent Diffusion for Inverse Problems
HTML
PDF
Amir Nazemi, Mohammad Hadi Sepanj, Nicholas Pellegrino, Chris Czarnecki, Paul Fieguth
TL;DR
本研究针对图像逆问题中现有方法未充分探索解空间的不足，提出了一种基于粒子滤波的潜在扩散方法。该方法通过初始阶段的非线性解空间探索，显著提升了超分辨率、去模糊和图像修复任务的解决效果，超越了当前最先进的PSLD求解器。
Abstract
Current strategies for solving image-based
Inverse Problems
apply
Latent Diffusion
models to perform posterior sampling.However, almost all approaches make no explicit attempt to explore the solution space, inste
→