使用序贯蒙特卡洛在潜空间中进行逆问题采样
Inverse Problem Sampling in Latent Space Using Sequential Monte Carlo
AI总结：
本文提出LD-SMC方法，在扩散模型潜空间中利用序贯蒙特卡洛进行后验推断，以解决图像逆问题条件采样难题，并在ImageNet和FFHQ上验证其在修复等任务中的优势。
摘要：
在图像处理中，求解逆问题是指为被某种（通常是已知的）退化算子破坏的图像寻找合理重建结果的任务。通常，这一过程借助生成式图像模型来完成，该模型能够引导重建朝着看起来自然的解的方向进行。过去几年中扩散模型的成功使其成为该任务的主要候选方法。然而，扩散模型的序贯特性使得这种条件采样过程具有挑战性。此外，由于扩散模型通常定义在自编码器的潜空间中，编码器-解码器变换引入了额外的困难。为应对这些挑战，我们提出了一种基于序贯蒙特卡洛（SMC）的新颖采样方法，该方法在扩散模型的潜空间中运行。我们将该方法命名为LD-SMC。我们利用额外的辅助观测为数据定义了一个生成模型，并基于反向扩散过程使用SMC采样进行后验推断。在ImageNet和FFHQ上的实证评估表明，LD-SMC在各种逆问题任务中，尤其是在具有挑战性的图像修复任务中，相较于竞争方法具有优势。
英文摘要：
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.
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。
