mlsanityData to 7 Oct 2026

Product-of-Gaussian-Mixture Diffusion Models for Joint Nonlinear MRI Reconstruction

arXiv 2605.10629 ↗First posted 11 May 2026cs.CVcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Recently, diffusion models have attracted considerable attention for magnetic resonance image reconstruction due to their high sample quality. However, most existing methods rely on large networks with opaque time-conditioning mechanisms, and require offline coil sensitivity estimation. This results in limited interpretability of the reconstruction process and reduced flexibility in the acquisition setup. To address these limitations, we jointly reconstruct the image and the coil sensitivities by combining the parameter-efficient product-of-Gaussian-mixture diffusion model as an image prior with a classical smoothness prior on the coil sensitivities. The proposed method is fast and robust to both contrast and anatomical distribution shifts as well as changing k-space trajectories. Finally, we propose a more expressive parameterization of the image prior which improves results in denoising and magnetic resonance image reconstruction.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 33 of its 83 references that are in the map. First posted on arXiv 11 May 2026.

Builds on

33 of 83 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Product of Gaussian Mixture Diffusion Model for non-linear MRI Inversion15 Jan
  2. 2025Bigger Isn't Always Better: Towards a General Prior for Medical Image Reconstruction13 Jan
  3. 2023Joint Non-Linear MRI Inversion with Diffusion Priors23 Oct
  4. 2022Bayesian MRI Reconstruction with Joint Uncertainty Estimation using Diffusion Models3 Feb
  5. 2021Score-based diffusion models for accelerated MRI8 Oct

Other references · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  6. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  7. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  8. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  9. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  10. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 407
  11. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 384
  12. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 340
16 more
  1. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
  2. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  3. 2020AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradientscited by 282
  4. 2020End-to-End Variational Networks for Accelerated MRI Reconstructioncited by 201
  5. 2015Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restorationcited by 194
  6. 2024A Survey on Diffusion Models for Inverse Problemscited by 173
  7. 2022Parallel Diffusion Models of Operator and Image for Blind Inverse Problemscited by 113
  8. 2021Estimating High Order Gradients of the Data Distribution by Denoisingcited by 63
  9. 2023GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restorationcited by 58
  10. 2022Stable Deep MRI Reconstruction using Generative Priorscited by 21
  11. 2021Deep J-Sense: Accelerated MRI Reconstruction via Unrolled Alternating Optimizationcited by 19
  12. 2014Insights into analysis operator learning: From patch-based sparse models to higher-order MRFscited by 18
  13. 2021MRI Reconstruction Using Deep Energy-Based Modelcited by 8
  14. 2023Product of Gaussian Mixture Diffusion Modelscited by 6
  15. 2025Energy-based models for inverse imaging problemscited by 4
  16. 2024ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI Reconstructioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Diffusion Modeling with Domain-conditioned Prior Guidance for Accelerated MRI and qMRI Reconstruction
  2. 2023Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models
  3. 2025Conditional Denoising Diffusion Model-Based Robust MR Image Reconstruction from Highly Undersampled Data
  4. 2024On Instabilities of Unsupervised Denoising Diffusion Models in Magnetic Resonance Imaging Reconstruction
  5. 2025Fast and Robust Diffusion Posterior Sampling for MR Image Reconstruction Using the Preconditioned Unadjusted Langevin Algorithm
  6. 2024LDPM: Towards undersampled MRI reconstruction with MR-VAE and Latent Diffusion Prior
  7. 2023CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?
  8. 2026High-dimensional Embedding Prior for Noisy K-space Domain MRIReconstruction