# FusionNet: a frame interpolation network for 4D heart models

arXiv: https://arxiv.org/abs/2603.10212 · HTML: https://mlsanity.com/paper/2603.10212/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 10 Mar 2026.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation](https://mlsanity.com/paper/2012.08512/) (2020)
- [Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequences](https://mlsanity.com/paper/1806.04066/) (2018)
- [Robust Deep Multi-modal Learning Based on Gated Information Fusion Network](https://mlsanity.com/paper/1807.06233/) (2018)
- [Explainable Anatomical Shape Analysis through Deep Hierarchical Generative Models](https://mlsanity.com/paper/1907.00058/) (2019)
- [Cine Cardiac MRI Motion Artifact Reduction Using a Recurrent Neural Network](https://mlsanity.com/paper/2006.12700/) (2020)
- [Efficient and Phase-aware Video Super-resolution for Cardiac MRI](https://mlsanity.com/paper/2005.10626/) (2020)

## Abstract (arXiv)

Cardiac magnetic resonance (CMR) imaging is widely used to visualise cardiac motion and diagnose heart disease. However, standard CMR imaging requires patients to lie still in a confined space inside a loud machine for 40-60 min, which increases patient discomfort. In addition, shorter scan times decrease either or both the temporal and spatial resolutions of cardiac motion, and thus, the diagnostic accuracy of the procedure. Of these, we focus on reduced temporal resolution and propose a neural network called FusionNet to obtain four-dimensional (4D) cardiac motion with high temporal resolution from CMR images captured in a short period of time. The model estimates intermediate 3D heart shapes based on adjacent shapes. The results of an experimental evaluation of the proposed FusionNet model showed that it achieved a performance of over 0.897 in terms of the Dice coefficient, confirming that it can recover shapes more precisely than existing methods. This code is available at: https://github.com/smiyauchi199/FusionNet.git