# A Generative Shape Compositional Framework to Synthesise Populations of Virtual Chimaeras

arXiv: https://arxiv.org/abs/2210.01607 · HTML: https://mlsanity.com/paper/2210.01607/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 69 references that are in the map.
- First posted on arXiv 4 Oct 2022.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [Generating 3D faces using Convolutional Mesh Autoencoders](https://mlsanity.com/paper/1807.10267/) (2018)
- [Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge](https://mlsanity.com/paper/1902.07880/) (2019)
- [DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets](https://mlsanity.com/paper/2011.10217/) (2020)
- [Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels](https://mlsanity.com/paper/2006.04325/) (2020)
- [Deformable Shape Completion with Graph Convolutional Autoencoders](https://mlsanity.com/paper/1712.00268/) (2017)
- [Learning Part Generation and Assembly for Structure-aware Shape Synthesis](https://mlsanity.com/paper/1906.06693/) (2019)
- [Parametric Exponential Linear Unit for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1605.09332/) (2016)
- [Composite Shape Modeling via Latent Space Factorization](https://mlsanity.com/paper/1901.02968/) (2019)
- [EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation](https://mlsanity.com/paper/2110.06679/) (2021)
- [DiDA: Disentangled Synthesis for Domain Adaptation](https://mlsanity.com/paper/1805.08019/) (2018)
- [Handling confounding variables in statistical shape analysis -- application to cardiac remodelling](https://mlsanity.com/paper/2007.14239/) (2020)

## Built on by (most cited first, 5 of 5)

- [A personalized time-resolved 3D mesh generative model for unveiling normal heart dynamics](https://mlsanity.com/paper/2409.13825/) (2024)
- [End-to-End 4D Heart Mesh Recovery Across Full-Stack and Sparse Cardiac MRI](https://mlsanity.com/paper/2509.12090/) (2025)
- [CardioComposer: Leveraging Differentiable Geometry for Compositional Control of Anatomical Diffusion Models](https://mlsanity.com/paper/2509.08015/) (2025)
- [Conditional Latent Diffusion Model with Fourier-based Motion Modelling for Virtual Population Synthesis](https://mlsanity.com/paper/2606.03827/) (2026)
- [HeartVolMesh: Cardiac Volumetric Mesh Reconstruction via Covariance-Guided Graph Deformation](https://mlsanity.com/paper/2607.04243/) (2026)

## Abstract (arXiv)

Generating virtual populations of anatomy that capture sufficient variability while remaining plausible is essential for conducting in-silico trials of medical devices. However, not all anatomical shapes of interest are always available for each individual in a population. Hence, missing/partially-overlapping anatomical information is often available across individuals in a population. We introduce a generative shape model for complex anatomical structures, learnable from datasets of unpaired datasets. The proposed generative model can synthesise complete whole complex shape assemblies coined virtual chimaeras, as opposed to natural human chimaeras. We applied this framework to build virtual chimaeras from databases of whole-heart shape assemblies that each contribute samples for heart substructures. Specifically, we propose a generative shape compositional framework which comprises two components - a part-aware generative shape model which captures the variability in shape observed for each structure of interest in the training population; and a spatial composition network which assembles/composes the structures synthesised by the former into multi-part shape assemblies (viz. virtual chimaeras). We also propose a novel self supervised learning scheme that enables the spatial composition network to be trained with partially overlapping data and weak labels. We trained and validated our approach using shapes of cardiac structures derived from cardiac magnetic resonance images available in the UK Biobank. Our approach significantly outperforms a PCA-based shape model (trained with complete data) in terms of generalisability and specificity. This demonstrates the superiority of the proposed approach as the synthesised cardiac virtual populations are more plausible and capture a greater degree of variability in shape than those generated by the PCA-based shape model.