aiqbench analysis
This paper introduces CM-RED, a method that leverages consistency models to accelerate MRI reconstruction within the regularization by denoising framework. By integrating controlled noise injection into proximal gradient updates, it achieves high-fidelity imaging with only four network function evaluations, significantly outperforming standard diffusion model approaches. The work demonstrates practical viability for medical imaging applications where speed and generative diversity are critical constraints.
Consistency Models for Fast MRI Reconstruction Using Regularization by Denoising
arXiv:2608.20561v1 Announce Type: cross Abstract: Diffusion models (DMs) have emerged as powerful generative priors for MRI reconstruction with promising results. Yet DM-based methods require extensive iterative refinement, limiting their practical deployment. Consistency models (CMs) provide a compelling alternative, aiming to map out the diffusion trajectory in a single pass, enabling faster generation. In this work, we propose CM-RED, a novel MRI reconstruction method that integrates a pretrained CM into the regularization by denoising (RED) scheme. Our method builds on accelerated proximal gradient RED (RED-APG), and further incorporates controlled noise injection during the update steps to enhance generative diversity and accelerate convergence. Extensive experiments on the fastMRI knee and brain datasets demonstrate that CM-RED achieves high-quality reconstructions across multiple anatomies, contrast weights, acceleration factors, and undersampling patterns, using only 4 network function evaluations (NFEs). The proposed method consistently outperforms existing DM- and CM-based approaches in both quantitative metrics and visual fidelity, and exhibits strong robustness to hyperparameter variations, highlighting CM-RED as an efficient and effective generative framework for accelerated MRI reconstruction. The source code and pretrained models are publicly available at https://github.com/MerveGulle/CM-RED.
Abstract:Diffusion models (DMs) have emerged as powerful generative priors for MRI reconstruction with promising results. Yet DM-based methods require extensive iterative refinement, limiting their practical deployment. Consistency models (CMs) provide a compelling alternative, aiming to map out the diffusion trajectory in a single pass, enabling faster generation. In this work, we propose CM-RED, a novel MRI reconstruction method that integrates a pretrained CM into the regularization by denoising (RED) scheme. Our method builds on accelerated proximal gradient RED (RED-APG), and further incorporates controlled noise injection during the update steps to enhance generative diversity and accelerate convergence. Extensive experiments on the fastMRI knee and brain datasets demonstrate that CM-RED achieves high-quality reconstructions across multiple anatomies, contrast weights, acceleration factors, and undersampling patterns, using only 4 network function evaluations (NFEs). The proposed method consistently outperforms existing DM- and CM-based approaches in both quantitative metrics and visual fidelity, and exhibits strong robustness to hyperparameter variations, highlighting CM-RED as an efficient and effective generative framework for accelerated MRI reconstruction. The source code and pretrained models are publicly available at this https URL.
Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Medical Physics (physics.med-ph)
arXiv:2608.20561 [eess.IV]
(or arXiv:2608.20561v1 [eess.IV] for this version)
https://doi.org/10.48550/arXiv.2608.20561 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 213 words
Related coverage
Latent reasoning architectures would likely undermine CoT, our strongest oversight tool
AI Alignment Forum · Sep 23, 2026
Presentation: Beyond Prompting: Context Engineering and Memory Management for AI Systems at Scale
InfoQ · Jun 10, 2026
Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstruction
arXiv · Sep 3, 2026
A Physics-Informed Hybrid Neural Operator for Transient Magnetization Prediction in Power Magnetics
arXiv · Aug 5, 2026