# UMPIRE-Net: Unrolled Magnitude-Phase Regularization Network for Accelerated MRI

arXiv: https://arxiv.org/abs/2608.14422 · HTML: https://mlsanity.com/paper/2608.14422/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 14 Aug 2026.

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

- [MoDL: Model Based Deep Learning Architecture for Inverse Problems](https://mlsanity.com/paper/1712.02862/) (2017)
- [Learning a Variational Network for Reconstruction of Accelerated MRI Data](https://mlsanity.com/paper/1704.00447/) (2017)
- [Deep Learning Methods for Parallel Magnetic Resonance Image Reconstruction](https://mlsanity.com/paper/1904.01112/) (2019)
- [Deep Residual Learning for Accelerated MRI using Magnitude and Phase Networks](https://mlsanity.com/paper/1804.00432/) (2018)
- [Nesterov Accelerated ADMM for Fast Diffeomorphic Image Registration](https://mlsanity.com/paper/2109.12688/) (2021)
- [Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM](https://mlsanity.com/paper/2510.05544/) (2025)
- [General Phase Regularized Reconstruction using Phase Cycling](https://mlsanity.com/paper/1709.05374/) (2017)
- [Time-Embedded Algorithm Unrolling for Computational MRI](https://mlsanity.com/paper/2510.16321/) (2025)

## Built on by (most cited first, 2 of 2)

- [Harnessing Magnitude-Only and Complex Measurements for Improved Dynamic MRI Reconstruction with Learned Priors](https://mlsanity.com/paper/2608.18036/) (2026)
- [Consistency Models for Fast MRI Reconstruction Using Regularization by Denoising](https://mlsanity.com/paper/2608.20561/) (2026)

## Abstract (arXiv)

MRI reconstruction from undersampled k-space measurements is an ill-posed inverse problem. Physics-driven deep learning (PD-DL) methods have shown strong performance for this task by combining the MRI forward model with learned image regularization within algorithm-unrolling frameworks. However, most existing PD-DL methods reconstruct complex-valued images directly, thereby implicitly coupling magnitude and phase within a single learned representation. This coupled regularization may be suboptimal in reconstruction settings where accurate phase modeling plays an important role, such as partial Fourier (PF) imaging, where recovery of the omitted asymmetric k-space measurements depends on the underlying image phase. In such scenarios, explicit modeling of magnitude and phase as separate components may reduce the reliance on externally estimated or predefined phase information. To this end, we propose UMPIRE-Net (Unrolled Magnitude-Phase In REgularization Network), a PD-DL method that introduces separate learned regularizers for magnitude and phase components, together with a novel data-fidelity formulation that enforces measurements consistency. We evaluate UMPIRE-Net for accelerated MRI with PF across different datasets and acceleration factors. Experimental results demonstrate that our proposed method improves reconstruction quality compared with a conventional complex-valued PD-DL baseline, yielding sharper images and reduced artifacts. Code available at: https://github.com/MahdiSaberii/UMPIRE-Net