Fast and Explicit: Slice-to-Volume Reconstruction via 3D Gaussian Primitives with Analytic Point Spread Function Modeling

Maik Dannecker, Steven Jia, Nil Stolt-Ansó, Nadine Girard, Guillaume Auzias, François Rousseau, Daniel Rueckert

Keywords: Slice-to-Volume Reconstruction, 3D Gaussian Splatting, Super-Resolution, Fetal MRI, Neonatal MRI.

TL;DR: We propose explicit Gaussian primitives with closed-form analytic PSF modeling for fetal SVR, achieving state-of-the-art reconstruction 10x faster than implicit neural networks.

Abstract: Recovering high-fidelity 3D images from sparse or degraded 2D images is a fundamental challenge in medical imaging, with broad applications ranging from 3D ultrasound reconstruction to MRI super-resolution. In the context of fetal MRI, high-resolution 3D reconstruction of the brain from motion-corrupted low-resolution 2D acquisitions is a prerequisite for accurate neurodevelopmental diagnosis. While implicit neural representations (INRs) have recently established state-of-the-art performance in self-supervised slice-to-volume reconstruction (SVR), they suffer from a critical computational bottleneck: accurately modeling the image acquisition physics requires expensive stochastic Monte Carlo sampling to approximate the point spread function (PSF). In this work, we propose a shift from neural network based implicit representations to Gaussian based explicit representations. By parameterizing the HR 3D image volume as a field of anisotropic Gaussian primitives, we leverage the property of Gaussians being closed under convolution and thus derive a \textit{closed-form analytical solution} for the forward model. This formulation reduces the previously intractable acquisition integral to an exact covariance addition ($\mathbf{\Sigma}{obs} = \mathbf{\Sigma}{HR} + \mathbf{\Sigma}{PSF}$), effectively bypassing the need for compute-intensive stochastic sampling while ensuring exact gradient propagation. We demonstrate that our approach matches the reconstruction quality of self-supervised state-of-the-art SVR frameworks while delivering a 5$\times$--10$\times$ speed-up on neonatal and fetal data. With convergence often reached in under 30 seconds, our framework paves the way towards translation into clinical routine of real-time fetal 3D MRI. Code will be public at \href{https://github.com/m-dannecker/Gaussian-Primitives-for-Fast-SVR}{https://github.com/m-dannecker/Gaussian-Primitives-for-Fast-SVR}.

Primary Subject Area: Image Acquisition and Reconstruction

Secondary Subject Area: Unsupervised Learning and Representation Learning

Registration Requirement: Yes

Reproducibility: https://github.com/m-dannecker/Gaussian-Primitives-for-Fast-SVR

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 116