# Steerable Anatomical Shape Synthesis with Implicit Neural Representations

arXiv: https://arxiv.org/abs/2504.03313 · HTML: https://mlsanity.com/paper/2504.03313/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 4 Apr 2025.

## Builds on (most cited first, 8 of 8)

- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [From data to functa: Your data point is a function and you can treat it like one](https://mlsanity.com/paper/2201.12204/) (2022)
- [A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation](https://mlsanity.com/paper/2104.07645/) (2021)
- [Learning Smooth Neural Functions via Lipschitz Regularization](https://mlsanity.com/paper/2202.08345/) (2022)
- [Generative modeling of living cells with SO(3)-equivariant implicit neural representations](https://mlsanity.com/paper/2304.08960/) (2023)
- [Manipulating Vehicle 3D Shapes through Latent Space Editing](https://mlsanity.com/paper/2410.23931/) (2024)

## Built on by (most cited first, 3 of 3)

- [OSCAR: Occupancy-based Shape Completion via Acoustic Neural Implicit Representations](https://mlsanity.com/paper/2603.08279/) (2026)
- [CardioComposer: Leveraging Differentiable Geometry for Compositional Control of Anatomical Diffusion Models](https://mlsanity.com/paper/2509.08015/) (2025)
- [Anatomica: Localized Control over Geometric and Topological Properties for Anatomical Diffusion Models](https://mlsanity.com/paper/2511.20587/) (2025)

## Abstract (arXiv)

Generative modeling of anatomical structures plays a crucial role in virtual imaging trials, which allow researchers to perform studies without the costs and constraints inherent to in vivo and phantom studies. For clinical relevance, generative models should allow targeted control to simulate specific patient populations rather than relying on purely random sampling. In this work, we propose a steerable generative model based on implicit neural representations. Implicit neural representations naturally support topology changes, making them well-suited for anatomical structures with varying topology, such as the thyroid. Our model learns a disentangled latent representation, enabling fine-grained control over shape variations. Evaluation includes reconstruction accuracy and anatomical plausibility. Our results demonstrate that the proposed model achieves high-quality shape generation while enabling targeted anatomical modifications.