ResPF: Residual Poisson Flow for Efficient and Physically Consistent Sparse-View CT Reconstruction

2025-06-06

AI Summary

Sparse-angle, low-dose CT reconstruction suffers from ill-posed inverse problems; existing deep learning and diffusion-based methods often compromise physical interpretability or computational efficiency. This paper proposes the first Poisson-flow generative modeling framework tailored for CT reconstruction, explicitly embedding the physical measurement process into the generative dynamics. We design a residual-fusion ODE solver to ensure trajectory continuity, introduce a measurement-guided hijacking sampling strategy for efficient data-consistency enforcement, and integrate electrodynamics-inspired field modeling with conditional PFGM++. Evaluated on both synthetic and clinical datasets, our method outperforms state-of-the-art approaches in PSNR and SSIM, achieves 2.3× faster inference, and demonstrates superior robustness to noise and angular undersampling—achieving high-fidelity reconstruction, low computational overhead, and strong physical interpretability.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Sparse-view computed tomography (CT) is a practical solution to reduce radiation dose, but the resulting ill-posed inverse problem poses significant challenges for accurate image reconstruction. Although deep learning and diffusion-based methods have shown promising results, they often lack physical interpretability or suffer from high computational costs due to iterative sampling starting from random noise. Recent advances in generative modeling, particularly Poisson Flow Generative Models (PFGM), enable high-fidelity image synthesis by modeling the full data distribution. In this work, we propose Residual Poisson Flow (ResPF) Generative Models for efficient and accurate sparse-view CT reconstruction. Based on PFGM++, ResPF integrates conditional guidance from sparse measurements and employs a hijacking strategy to significantly reduce sampling cost by skipping redundant initial steps. However, skipping early stages can degrade reconstruction quality and introduce unrealistic structures. To address this, we embed a data-consistency into each iteration, ensuring fidelity to sparse-view measurements. Yet, PFGM sampling relies on a fixed ordinary differential equation (ODE) trajectory induced by electrostatic fields, which can be disrupted by step-wise data consistency, resulting in unstable or degraded reconstructions. Inspired by ResNet, we introduce a residual fusion module to linearly combine generative outputs with data-consistent reconstructions, effectively preserving trajectory continuity. To the best of our knowledge, this is the first application of Poisson flow models to sparse-view CT. Extensive experiments on synthetic and clinical datasets demonstrate that ResPF achieves superior reconstruction quality, faster inference, and stronger robustness compared to state-of-the-art iterative, learning-based, and diffusion models.

Problem

• Efficient sparse-view CT reconstruction with physical consistency
• Reducing computational costs in diffusion-based CT reconstruction
• Ensuring fidelity to sparse measurements while maintaining trajectory continuity

Innovation

• Residual Poisson Flow for efficient CT reconstruction
• Conditional guidance and hijacking reduce sampling cost
• Residual fusion module ensures trajectory continuity