提出可保持点对应关系的扩散模型，生成逼真脑部形状数据
Point-Based Shape Representation Generation with a Correspondence-Preserving Diffusion Model
- 基于扩散模型生成带点对应关系的点云形状
- 在OASIS-3数据上生成逼真海马体形状，优于现有方法
- 适用于健康与阿尔茨海默病患者的条件生成和疾病预测
我们提出一种扩散模型，用于生成保留点对应关系的点基形状表示。传统统计形状模型虽重视点对应，但当前深度学习方法多关注无序点云，忽略对应关系。现有点云生成模型也无法生成具有点间对应性的形状。本工作旨在构建一种能生成真实点基形状且保留训练数据中点对应关系的扩散模型。利用来自开放影像研究系列3（OASIS-3）的带对应关系的形状数据，我们证明该模型能有效生成高度逼真的海马体点云形状，优于现有方法。进一步通过下游任务验证其应用价值，包括健康与阿尔茨海默病患者条件生成，以及基于反事实生成预测疾病进展中的形态变化。
原文摘要 · Abstract (English)
We propose a diffusion model designed to generate point-based shape representations with correspondences. Traditional statistical shape models have considered point correspondences extensively, but current deep learning methods do not take them into account, focusing on unordered point clouds instead. Current deep generative models for point clouds do not address generating shapes with point correspondences between generated shapes. This work aims to formulate a diffusion model that is capable of generating realistic point-based shape representations, which preserve point correspondences that are present in the training data. Using shape representation data with correspondences derived from Open Access Series of Imaging Studies 3 (OASIS-3), we demonstrate that our correspondence-preserving model effectively generates point-based hippocampal shape representations that are highly realistic compared to existing methods. We further demonstrate the applications of our generative model by downstream tasks, such as conditional generation of healthy and AD subjects and predicting morphological changes of disease progression by counterfactual generation.
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。