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

Shen Zhu, Yinzhu Jin, Ifrah Zawar, Tom Fletcher
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:1930-1942, 2026.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-zhu26a, title = {Point-Based Shape Representation Generation with a Correspondence-Preserving Diffusion Model}, author = {Zhu, Shen and Jin, Yinzhu and Zawar, Ifrah and Fletcher, Tom}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {1930--1942}, year = {2026}, editor = {Tasdizen, Tolga and Elhabian, Shireen and Summers, Ronald and Chen, Chen and Koch, Lisa and Zhuang, Yan}, volume = {301}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v301/main/assets/zhu26a/zhu26a.pdf}, url = {https://proceedings.mlr.press/v301/zhu26a.html}, 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.} }
Endnote
%0 Conference Paper %T Point-Based Shape Representation Generation with a Correspondence-Preserving Diffusion Model %A Shen Zhu %A Yinzhu Jin %A Ifrah Zawar %A Tom Fletcher %B Proceedings of The 8th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Tolga Tasdizen %E Shireen Elhabian %E Ronald Summers %E Chen Chen %E Lisa Koch %E Yan Zhuang %F pmlr-v301-zhu26a %I PMLR %P 1930--1942 %U https://proceedings.mlr.press/v301/zhu26a.html %V 301 %X 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.
APA
Zhu, S., Jin, Y., Zawar, I. & Fletcher, T.. (2026). Point-Based Shape Representation Generation with a Correspondence-Preserving Diffusion Model. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:1930-1942 Available from https://proceedings.mlr.press/v301/zhu26a.html.

Related Material