发表机构
University of Virginia; University of Pittsburgh（弗吉尼亚大学; 匹兹堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出CLIMB-Flow算法，利用多尺度金字塔架构和近似吉布斯采样，在像素域实现高效后验采样，在多个图像任务上显著提升PSNR。
AI 中文摘要
扩散模型现在被广泛用作贝叶斯逆问题（特别是在成像领域）中的先验，其中潜在扩散模型通常用于较大规模的问题，以保持计算复杂度和模型规模的可管理性。不幸的是，基于自编码器的压缩会导致空间细节的丢失。此外，优化被转化为非线性问题。在本文中，我们引入了一种针对金字塔/级联架构定制的后验采样算法，该算法依赖于从粗到细的分层策略在像素域中生成图像。我们提出了CLIMB-Flow，它在三个步骤之间交替进行：从当前粗噪声图像进行端点估计，对干净图像进行数据一致性更新，并将其重新加噪回到网络期望的水平。这些步骤共同通过从两个条件分布进行近似吉布斯采样来在该尺度下对后验进行采样。在ImageNet、CelebA、AFHQ和fastMRI上的实验涵盖了图像修复、去模糊、超分辨率和加速MRI，在CelebA上相比最强竞争方法获得了1.37-7.66 dB的PSNR增益，并实现了高达512x512的像素域重建。
英文摘要
Diffusion models are now widely used in Bayesian inverse problems in imaging as priors, where latent diffusion models are often used for larger scale problems to keep the computational complexity and model-size manageable. Unfortunately, the auto-encoder based compression results in loss of spatial detail. In addition, the optimization is converted to a non-linear problem. In this paper, we introduce a posterior sampling algorithm customized for the pyramidal/cascaded architecture, which relies on a coarse to fine hierarchical strategy to generate images in the pixel domain. We present CLIMB-Flow which alternates between three steps: an end-point estimation from the current coarse and noisy image, data-consistent update of the clean image, and re-noising it back to the level the network expects. Together these steps sample the posterior at that scale using an approximate Gibbs sampling from two conditional distributions. Experiments on ImageNet, CelebA, AFHQ and fastMRI span inpainting, deblurring, super-resolution and accelerated MRI, with PSNR gains of 1.37-7.66 dB over the strongest competing method on CelebA and pixel-domain reconstruction up to 512x512.
Comments5 pages, 3 figures, 1 table. Submitted to ICASSP 2027
