用粒子采样在扩散模型隐空间解决图像逆问题，提升修复效果。
Inverse Problem Sampling in Latent Space Using Sequential Monte Carlo
- 基于序列蒙特卡洛在隐空间迭代采样，结合反向扩散过程推理
- 在ImageNet和FFHQ上显著优于现有方法，尤其在修补任务中表现突出
- 适合需要高质量图像重建的科研与工业应用
在图像处理中，求解逆问题是寻找被已知退化算子破坏的图像的合理重构。通常通过生成式图像模型引导重建结果趋向自然外观。近年来扩散模型因其优异表现成为该任务的主流选择。然而，扩散模型的序列特性使条件采样面临挑战，且其常定义于自编码器的隐空间，编码-解码变换带来额外困难。为此，本文提出一种基于序列蒙特卡洛（SMC）的新型采样方法——LD-SMC，利用附加辅助观测构建数据生成模型，并基于反向扩散过程进行后验推断。在ImageNet和FFHQ上的实证评估表明，LD-SMC在多种逆问题任务中均优于现有方法，尤其在高难度修复任务中优势明显。
原文摘要 · Abstract (English)
In image processing, solving inverse problems is the task of finding plausible reconstructions of an image that was corrupted by some (usually known) degradation operator. Commonly, this process is done using a generative image model that can guide the reconstruction towards solutions that appear natural. The success of diffusion models over the last few years has made them a leading candidate for this task. However, the sequential nature of diffusion models makes this conditional sampling process challenging. Furthermore, since diffusion models are often defined in the latent space of an autoencoder, the encoder-decoder transformations introduce additional difficulties. To address these challenges, we suggest a novel sampling method based on sequential Monte Carlo (SMC) in the latent space of diffusion models. We name our method LD-SMC. We define a generative model for the data using additional auxiliary observations and perform posterior inference with SMC sampling based on a reverse diffusion process. Empirical evaluations on ImageNet and FFHQ show the benefits of LD-SMC over competing methods in various inverse problem tasks and especially in challenging inpainting tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。