The paper introduces a high‑resolution Rectified Flow Matching model trained on 256×256 chest CT images to serve as a generative prior for CT reconstruction. A two‑stage training strategy—initial strong anatomically informed augmentation followed by fine‑tuning—helps mitigate overfitting and improve structural fidelity. When evaluated on various CT inverse problems, Flow Matching‑based reconstruction methods outperform diffusion‑based algorithms in PSNR, SSIM, and perceptual quality while requiring fewer sampling steps.
By Davide Evangelista
arXiv:2606. 06236v1 Announce Type: new Abstract: Pretrained diffusion models demonstrate impressive potential in solving highly ill-posed 3D computed tomography (CT) inverse problems, while the inference process suffers from significant computational overhead.
By Yujia Wu, Zhaoqiang Liu
arXiv:2606. 16212v1 Announce Type: cross Abstract: Sparse-view CT reduces radiation dose and scanning time by acquiring fewer projection views, but angular undersampling makes reconstruction severely ill-posed, causing streak artifacts, structural blurring, and loss of fine details.
By Jigang Duan, Jiayi Wang, Heran Wang, Ping Yang, Genwei Ma, Xing Zhao
The paper introduces CM-RED, a fast MRI reconstruction method that combines a pretrained consistency model with the regularization by denoising framework. By integrating controlled noise injection into accelerated proximal gradient updates, CM-RED achieves high‑quality reconstructions on fastMRI knee and brain datasets with only four network function evaluations. It consistently outperforms existing diffusion‑ and consistency‑based approaches in quantitative metrics, visual fidelity, and robustness to hyperparameter changes.
By Merve G\"ulle, Junno Yun, Ya\c{s}ar Utku Al\c{c}alar, Mehmet Ak\c{c}akaya
arXiv:2607. 11941v1 Announce Type: cross Abstract: Computed tomography (CT) is a critical imaging modality for clinical diagnosis, but reducing radiation dose inevitably introduces severe noise and structured artifacts that degrade image quality.
By Md Imam Ahasan, Guangchao Yang, A F M Abdun Noor, Kah Ong Michael Goh, S. M. Hasan Mahmud, Md Mahfuzur Rahman
The paper introduces Conditional Diffusion Posterior Alignment (CDPA), a method that scales diffusion-based sparse‑view CT reconstruction to large 3D volumes by conditioning a 2D U‑Net diffusion model on an initial 3D reconstruction and enforcing data‑consistency alignment. CDPA addresses high memory demands, limited 3D training data, and slice‑wise inconsistencies, achieving state‑of‑the‑art performance on synthetic and real Cone Beam CT data. The authors also demonstrate that the same approach improves fast denoising U‑Nets, delivering near‑diffusion quality at a fraction of the computational cost.
By Luis Barba, Johannes Kirschner, Benjamin Bejar
arXiv:2508. 05321v4 Announce Type: replace-cross Abstract: Assume you encounter an inverse problem that shall be solved for a large number of data, but no ground-truth data is available.
By Laura Hellwege, Johann Christopher Engster, Moritz Schaar, Thorsten M. Buzug, Maik Stille
arXiv:2602. 23214v2 Announce Type: replace-cross Abstract: Plug-and-Play diffusion prior (PnPDP) frameworks have emerged as a powerful paradigm for solving imaging inverse problems by treating pretrained generative models as modular priors.
By Chenhe Du, Xuanyu Tian, Qing Wu, Muyu Liu, Jingyi Yu, Hongjiang Wei, Yuyao Zhang
The paper introduces MS-Flow, a method that represents a flow-based generative model’s trajectory as a sequence of intermediate latent states instead of a single initial code. By enforcing local flow dynamics and coupling trajectory segments with matching penalties, the approach alternates between updating latent states and ensuring consistency with observed data. This strategy reduces memory usage and improves reconstruction quality on tasks such as image inpainting, super‑resolution, and computed tomography.
By Alexander Denker, Zeljko Kereta, Carola-Bibiane Sch\"onlieb, Moshe Eliasof
FlowSGS introduces a flow-based posterior sampling method that combines Split Gibbs Sampling (SGS) with Langevin dynamics for the likelihood step and Stochastic Interpolants (SI) for the prior step. By integrating a pretrained flow model into the prior step via SI's reverse-time SDE and a novel timestep correction, FlowSGS reduces the number of network evaluations compared to plug‑and‑play diffusion samplers. Experiments demonstrate state‑of‑the‑art performance on various inverse problems, including the first flow‑based solution to a nonlinear inverse problem (Fourier phase retrieval).
By Tianao Li, Xinhui Qian, Emma Alexander
FlowMoDL is an unrolled neural network designed for highly accelerated 4D flow MRI reconstruction, optimizing both anatomical magnitude and phase-derived velocity accuracy. It alternates a learned (3+1)D spatiotemporal denoiser with conjugate‑gradient data‑consistency updates, using a dual‑pathway conditioning scheme to handle acceleration factors from 10× to 50×. Trained with a deep‑supervision composite loss that penalizes velocity magnitude and angular errors, FlowMoDL outperforms classical and deep‑learning baselines on the multi‑center CMRx4DFlow dataset, achieving superior gradient‑step efficiency and robust convergence across all acceleration factors.
By Tristan Gottwald, Michelle Bruch, Mubashir-Ul Hassan, Fatma Alickovic, Milan Kloiber, Daniel Tenbrinck, Torsten Panholzer, Melanie Schaller, Jana Hutter
arXiv:2511. 17038v4 Announce Type: replace Abstract: From a Bayesian perspective, score-based diffusion solves inverse problems through joint inference, embedding the likelihood with the prior to guide the sampling process.
By Hao Chen, Renzheng Zhang, Scott S. Howard