# Iterative Diffusion-Refined Neural Attenuation Fields for Multi-Source Stationary CT Reconstruction: NAF Meets Diffusion Model

arXiv: https://arxiv.org/abs/2511.14310 · HTML: https://mlsanity.com/paper/2511.14310/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 25 of its 59 references that are in the map.
- First posted on arXiv 18 Nov 2025.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [Neural Reflectance Fields for Appearance Acquisition](https://mlsanity.com/paper/2008.03824/) (2020)
- [Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models](https://mlsanity.com/paper/2211.10655/) (2022)
- [NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2209.14540/) (2022)
- [Implicit Neural Representation in Medical Imaging: A Comparative Survey](https://mlsanity.com/paper/2307.16142/) (2023)
- [Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CT](https://mlsanity.com/paper/1708.08333/) (2017)
- [Structure-Aware Sparse-View X-ray 3D Reconstruction](https://mlsanity.com/paper/2311.10959/) (2023)
- [Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fields](https://mlsanity.com/paper/2104.11745/) (2021)
- [Deep-neural-network based sinogram synthesis for sparse-view CT image reconstruction](https://mlsanity.com/paper/1803.00694/) (2018)
- [Generative Modeling in Sinogram Domain for Sparse-view CT Reconstruction](https://mlsanity.com/paper/2211.13926/) (2022)
- [SNAF: Sparse-view CBCT Reconstruction with Neural Attenuation Fields](https://mlsanity.com/paper/2211.17048/) (2022)
- [FreeSeed: Frequency-band-aware and Self-guided Network for Sparse-view CT Reconstruction](https://mlsanity.com/paper/2307.05890/) (2023)
- [Stage-by-stage Wavelet Optimization Refinement Diffusion Model for Sparse-View CT Reconstruction](https://mlsanity.com/paper/2308.15942/) (2023)
- [DPER: Diffusion Prior Driven Neural Representation for Limited Angle and Sparse View CT Reconstruction](https://mlsanity.com/paper/2404.17890/) (2024)
- [Learning to Distill Global Representation for Sparse-View CT](https://mlsanity.com/paper/2308.08463/) (2023)
- [Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction](https://mlsanity.com/paper/2303.14739/) (2023)
- [Unsupervised CT Metal Artifact Reduction by Plugging Diffusion Priors in Dual Domains](https://mlsanity.com/paper/2308.16742/) (2023)
- [Sinogram interpolation for sparse-view micro-CT with deep learning neural network](https://mlsanity.com/paper/1902.03362/) (2019)

## Abstract (arXiv)

Multi-source stationary computed tomography (CT) has recently attracted attention for its ability to achieve rapid image reconstruction, making it suitable for time-sensitive clinical and industrial applications. However, practical systems are often constrained by ultra-sparse-view sampling, which significantly degrades reconstruction quality. Traditional methods struggle under ultra-sparse-view settings, where interpolation becomes inaccurate and the resulting reconstructions are unsatisfactory. To address this challenge, this study proposes Diffusion-Refined Neural Attenuation Fields (Diff-NAF), an iterative framework tailored for multi-source stationary CT under ultra-sparse-view conditions. Diff-NAF combines a Neural Attenuation Field representation with a dual-branch conditional diffusion model. The process begins by training an initial NAF using ultra-sparse-view projections. New projections are then generated through an Angle-Prior Guided Projection Synthesis strategy that exploits inter view priors, and are subsequently refined by a Diffusion-driven Reuse Projection Refinement Module. The refined projections are incorporated as pseudo-labels into the training set for the next iteration. Through iterative refinement, Diff-NAF progressively enhances projection completeness and reconstruction fidelity under ultra-sparse-view conditions, ultimately yielding high-quality CT reconstructions. Experimental results on multiple simulated 3D CT volumes and real projection data demonstrate that Diff-NAF achieves the best performance under ultra-sparse-view conditions.