arXiv Machine Learning

Generative Translation Priors: Bayesian Imaging with Cross-Modality Image Translation

Generative Translation Priors (GTP) is a Bayesian framework that repurposes diffusion-based image-to-image translation models as cross-modality priors for ill‑posed imaging inverse problems. It incorporates target‑domain measurements via likelihood guidance, steering the translation toward the desired posterior distribution. The authors analyze the resulting posterior dynamics, identify an intrinsic bias from likelihood guidance, and propose a ground‑truth‑free metric to estimate this bias, leading to two discretized GTP algorithms that demonstrate high‑fidelity reconstruction in CT and PET imaging using complementary side information.

arXiv AI
Sep 4

A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors

The paper introduces a Posterior‑Dynamics Framework that leverages pretrained diffusion models as multiscale priors for linear imaging inverse problems such as deblurring, super‑resolution, and inpainting. By constructing a surrogate likelihood centered on the clean image and incorporating diffusion uncertainty, the authors derive continuous posterior dynamics and a tunable Langevin component for adaptive exploration. They prove theoretical guarantees (endpoint consistency, finite‑horizon tracking, weak accuracy) and present the PD‑IMEX sampler, which achieves high‑quality reconstructions with only 100 score evaluations and controllable fidelity‑diversity trade‑offs.

By Zhaoqiang Liu, Tongyao Pang, Ruibing Wang, Yang Zheng
arXiv AI
Jun 16

LUCID: Learned Undersampling-Adaptive Consistency-Guided Inference with Deterministic Flow Matching for Sparse-View CT Reconstruction

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
arXiv Machine Learning
Aug 19

Picard Proximal Monte Carlo for Parallel Bayesian Imaging with Score-Based Generative Priors

The paper introduces PiX-MC, a time‑parallel posterior sampling framework that combines proximal Langevin dynamics with Picard iteration for Bayesian imaging inverse problems. By leveraging efficient proximal operators for many imaging likelihoods and exploiting parallelism across discretization nodes, PiX-MC supports multi‑GPU implementation and includes multi‑block and annealed variants to enhance scalability. Experiments on various imaging tasks, including a large‑scale sparse‑view CT problem, show that PiX‑MC can reduce runtime by up to 50× while maintaining reconstruction quality.

By Deliang Wei, Evan Bell, Wenhan Guo, Yifan Chen, Yu Sun
arXiv Computer Vision
Aug 31

Physics-Guided Flow Matching for CT Image Reconstruction

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 Machine Learning
Jun 4

Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction

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
Hugging Face Trending Papers
Jun 23

Prob-BBDM: a Probabilistic Brownian Bridge Diffusion Model for MRI sequence image-to-image translation

AI-driven image-to-image synthesis is rapidly advancing, with growing applications in medical imaging. Multi-modal image analysis plays a crucial role in optimizing examination quality, yet acquiring multiple imaging modalities in clinical settings remains resource-intensive and time-consuming, especially for 3D imaging.

arXiv AI
1d ago

Dose-Aware Cold Diffusion with Physics Consistency for Generalizable Low-Dose CT Reconstruction

The paper introduces Dose-Aware Cold Diffusion (DACD), a physics-consistent framework that treats radiation dose as a continuous latent variable in a cold diffusion process for low-dose CT reconstruction. DACD combines dose-aware perception, multi-scale structural priors, and dose-calibrated step allocation to guide denoising, and adds an iterative forward-backprojection correction to enforce projection-domain consistency. Experiments on Mayo-2020, Mayo-2016, and LoDoPaB-CT show DACD outperforms existing diffusion-based and physics-guided methods, especially at ultra-low doses, and generalizes robustly across continuous, unseen dose levels.

By Md Imam Ahasan, Guangchao Yang, A F M Abdun Noor, S M Hasan Mahmud, Md Mahfuzur Rahman