# Systole-Conditioned Generative Cardiac Motion

arXiv: https://arxiv.org/abs/2507.15894 · HTML: https://mlsanity.com/paper/2507.15894/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 32 references that are in the map.
- First posted on arXiv 20 Jul 2025.

## Builds on (most cited first, 14 of 14)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [MedGAN: Medical Image Translation using GANs](https://mlsanity.com/paper/1806.06397/) (2018)
- [SADM: Sequence-Aware Diffusion Model for Longitudinal Medical Image Generation](https://mlsanity.com/paper/2212.08228/) (2022)
- [Endora: Video Generation Models as Endoscopy Simulators](https://mlsanity.com/paper/2403.11050/) (2024)
- [MulViMotion: Shape-aware 3D Myocardial Motion Tracking from Multi-View Cardiac MRI](https://mlsanity.com/paper/2208.00034/) (2022)
- [PCMC-T1: Free-breathing myocardial T1 mapping with Physically-Constrained Motion Correction](https://mlsanity.com/paper/2308.11281/) (2023)
- [7T MRI Synthesization from 3T Acquisitions](https://mlsanity.com/paper/2403.08979/) (2024)
- [Shape-consistent Generative Adversarial Networks for multi-modal Medical segmentation maps](https://mlsanity.com/paper/2201.09693/) (2022)
- [Synthetic Data Generation for 3D Myocardium Deformation Analysis](https://mlsanity.com/paper/2406.01040/) (2024)
- [CardioSpectrum: Comprehensive Myocardium Motion Analysis with 3D Deep Learning and Geometric Insights](https://mlsanity.com/paper/2407.03794/) (2024)

## Abstract (arXiv)

Accurate motion estimation in cardiac computed tomography (CT) imaging is critical for assessing cardiac function and surgical planning. Data-driven methods have become the standard approach for dense motion estimation, but they rely on vast amounts of labeled data with dense ground-truth (GT) motion annotations, which are often unfeasible to obtain. To address this limitation, we present a novel approach that synthesizes realistically looking pairs of cardiac CT frames enriched with dense 3D flow field annotations. Our method leverages a conditional Variational Autoencoder (CVAE), which incorporates a novel multi-scale feature conditioning mechanism and is trained to generate 3D flow fields conditioned on a single CT frame. By applying the generated flow field to warp the given frame, we create pairs of frames that simulate realistic myocardium deformations across the cardiac cycle. These pairs serve as fully annotated data samples, providing optical flow GT annotations. Our data generation pipeline could enable the training and validation of more complex and accurate myocardium motion models, allowing for substantially reducing reliance on manual annotations. Our code, along with animated generated samples and additional material, is available on our project page: https://shaharzuler.github.io/GenerativeCardiacMotion_Page.