Point-Based Shape Representation Generation with a Correspondence-Preserving Diffusion Model

TL;DR

This paper introduces a diffusion model that generates point-based shape representations with preserved point correspondences, enabling realistic shape synthesis and applications in medical imaging analysis.

Contribution

The work presents the first diffusion model specifically designed to generate point-based shapes with preserved correspondences, addressing a gap in deep learning shape generation methods.

Findings

Effectively generates realistic hippocampal shapes with preserved correspondences

Enables conditional generation of healthy and diseased shapes

Predicts morphological changes in disease progression

Abstract

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.