分层扩散模型提升医学影像超分辨率，更快更清晰。
Scale-Cascaded Diffusion Models for Super-Resolution in Medical Imaging
- 将图像分解为多尺度金字塔，每层训练独立扩散模型。
- 在脑、膝、前列腺MRI上提升视觉质量，推理速度更快。
- 适合需要高质量医学图像重建的研究者和临床应用。
扩散模型作为求解医学影像超分辨率等逆问题的强大生成先验，正被广泛应用。然而，现有方法通常仅使用单一尺度训练的扩散先验，忽略了图像数据的层次化尺度结构。本文提出将图像分解为拉普拉斯金字塔各层级，并为每个频率带训练独立的扩散先验。进而设计一种算法，利用这些先验在不同尺度上逐步精炼重建结果。在脑、膝及前列腺MRI数据集上的评估表明，该方法在提升感知质量的同时，通过使用更小的粗粒度网络降低了推理时间。本框架统一了多尺度重建与扩散先验，适用于医学图像超分辨率任务。
原文摘要 · Abstract (English)
Diffusion models have been increasingly used as strong generative priors for solving inverse problems such as super-resolution in medical imaging. However, these approaches typically utilize a diffusion prior trained at a single scale, ignoring the hierarchical scale structure of image data. In this work, we propose to decompose images into Laplacian pyramid scales and train separate diffusion priors for each frequency band. We then develop an algorithm to perform super-resolution that utilizes these priors to progressively refine reconstructions across different scales. Evaluated on brain, knee, and prostate MRI data, our approach both improves perceptual quality over baselines and reduces inference time through smaller coarse-scale networks. Our framework unifies multiscale reconstruction and diffusion priors for medical image super-resolution.
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。