Physics-Guided Flow Matching for CT Image Reconstruction

• URL: http://arxiv.org/abs/2608.28256v1
• Date: Fri, 28 Aug 2026 12:17:43 GMT
• Title: Physics-Guided Flow Matching for CT Image Reconstruction
• Abstract summary: Flow Matching is an alternative generative prior for high-resolution CT image reconstruction.<n>We train a high-resolution Rectified Flow Matching model on 256x256 chest images from the Mayo Clinic Low-Dose CT dataset.
• Score: 0.8460698440162889
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep generative models have recently emerged as powerful priors for solving ill-posed inverse problems in CT, with diffusion-based approaches achieving state-of-the-art reconstruction performance. However, diffusion models typically rely on stochastic sampling procedures, long inference trajectories, and carefully tuned noise schedules, which can limit computational efficiency and numerical stability, especially at high spatial resolutions. In this work, we investigate Flow Matching as an alternative generative prior for CT reconstruction. We train a high-resolution Rectified Flow Matching model on 256x256 chest images from the Mayo Clinic Low-Dose CT dataset. To mitigate overfitting and limited anatomical variability, we employ a two-stage training strategy consisting of an initial phase with strong, anatomically informed data augmentation, followed by a fine-tuning phase with reduced or no augmentation to refine structural fidelity. The resulting model is capable of generating high-quality and anatomically coherent CT-like images, serving as a strong learned prior. We then evaluate multiple reconstruction methods specifically designed for Flow Matching models, including Plug-and-Play Flow, FlowDPS, Flower, and Flow-Priors (ICTM), and compare them against state-of-the-art diffusion-based reconstruction algorithms such as DDRM, DPS, and DiffPIR. Experimental results across several CT inverse problem settings show that Flow Matching-based approaches consistently outperform diffusion-based methods in terms of PSNR, SSIM, and perceptual quality, while requiring fewer sampling steps. Finally, we publicly release the trained Flow Matching model and accompanying code to facilitate reproducibility and future research. Overall, this work demonstrates that Flow Matching provides a stable, efficient, and effective alternative to diffusion models for high-resolution CT image reconstruction.

Related papers

• Efficient Flow Matching for Sparse-View CT Reconstruction [7.05503627528473]
  Flow Matching (FM) models exhibit smooth trajectories without noise injection.<n>Motivated by this, we propose an FM-based CT reconstruction framework (FMCT)<n>We show that FMCT/EFMCT achieve competitive reconstruction quality while significantly improving computational efficiency compared with diffusion-based methods.
  arXiv  Detail & Related papers  (2026-02-27T11:13:43Z)
• Resolution-Independent Neural Operators for Multi-Rate Sparse-View CT [67.14700058302016]
  Deep learning methods achieve high-fidelity reconstructions but often overfit to a fixed acquisition setup.<n>We propose Computed Tomography neural Operator (CTO), a unified CT reconstruction framework that extends to continuous function space.<n>CTO enables consistent multi-sampling-rate and cross-resolution performance, with on average >4dB PSNR gain over CNNs.
  arXiv  Detail & Related papers  (2025-12-13T08:31:46Z)
• Tunable-Generalization Diffusion Powered by Self-Supervised Contextual Sub-Data for Low-Dose CT Reconstruction [5.107409624991683]
  TUnable-geneRalizatioN Diffusion (TurnDiff) is powered by self-supervised contextual sub-data for low-dose CT reconstruction.<n>TurnDiff consistently outperforms state-of-the-art methods in both reconstruction and generalization.
  arXiv  Detail & Related papers  (2025-09-28T13:50:29Z)
• Noise-Inspired Diffusion Model for Generalizable Low-Dose CT Reconstruction [37.71732274622662]
  We propose a noise-inspired diffusion model for generalizable low-dose CT reconstruction, termed NEED, which tailors diffusion models for noise characteristics of each domain.<n>By cascading these two diffusion models for dual-domain reconstruction, our NEED requires only normal-dose data for training and can be effectively extended to various unseen dose levels during testing.
  arXiv  Detail & Related papers  (2025-06-27T08:24:55Z)
• ResPF: Residual Poisson Flow for Efficient and Physically Consistent Sparse-View CT Reconstruction [7.644299873269135]
  Sparse-view computed tomography (CT) is a practical solution to reduce radiation dose, but the resulting inverse problem poses significant challenges for accurate image reconstruction.<n>Recent advances in generative modeling, particularly Poisson Flow Generative Models (PFGM), enable high-fidelity image synthesis.<n>We propose Residual Poisson Flow (ResPF) Generative Models for efficient and accurate sparse-view CT reconstruction.
  arXiv  Detail & Related papers  (2025-06-06T01:43:35Z)
• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Tomographic Foundation Model -- FORCE: Flow-Oriented Reconstruction Conditioning Engine [9.228750443979733]
  Deep learning has significantly advanced CT image reconstruction.<n>Deep learning methods can perform well with approximately paired data, but they inherently carry the risk of hallucination.<n>We propose a novel CT framework: Flow-Oriented Reconstruction Conditioning Engine (FORCE)
  arXiv  Detail & Related papers  (2025-06-02T18:25:12Z)
• Effective Diffusion Transformer Architecture for Image Super-Resolution [63.254644431016345]
  We design an effective diffusion transformer for image super-resolution (DiT-SR) In practice, DiT-SR leverages an overall U-shaped architecture, and adopts a uniform isotropic design for all the transformer blocks. We analyze the limitation of the widely used AdaLN, and present a frequency-adaptive time-step conditioning module.
  arXiv  Detail & Related papers  (2024-09-29T07:14:16Z)
• Timestep-Aware Diffusion Model for Extreme Image Rescaling [47.89362819768323]
  We propose a novel framework called Timestep-Aware Diffusion Model (TADM) for extreme image rescaling.<n>TADM performs rescaling operations in the latent space of a pre-trained autoencoder.<n>It effectively leverages powerful natural image priors learned by a pre-trained text-to-image diffusion model.
  arXiv  Detail & Related papers  (2024-08-17T09:51:42Z)
• Iterative CT Reconstruction via Latent Variable Optimization of Shallow Diffusion Models [1.4019041243188557]
  We propose a novel computed tomography (CT) reconstruction method by combining the denoising diffusion probabilistic model with iterative CT reconstruction. We demonstrated the effectiveness of the proposed method through the sparse-projection CT reconstruction of 1/10 projection data.
  arXiv  Detail & Related papers  (2024-08-06T12:55:17Z)
• Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models [75.52575380824051]
  We present a learning method to optimize sub-sampling patterns for compressed sensing multi-coil MRI. We use a single-step reconstruction based on the posterior mean estimate given by the diffusion model and the MRI measurement process. Our method requires as few as five training images to learn effective sampling patterns.
  arXiv  Detail & Related papers  (2023-06-05T22:09:06Z)
• Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
  Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance. We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-22T12:18:20Z)
• Normalizing Flows with Multi-Scale Autoregressive Priors [131.895570212956]
  We introduce channel-wise dependencies in their latent space through multi-scale autoregressive priors (mAR) Our mAR prior for models with split coupling flow layers (mAR-SCF) can better capture dependencies in complex multimodal data. We show that mAR-SCF allows for improved image generation quality, with gains in FID and Inception scores compared to state-of-the-art flow-based models.
  arXiv  Detail & Related papers  (2020-04-08T09:07:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.