mlsanityData to 14 Oct 2026

Regularizing INR with diffusion prior self-supervised 3D reconstruction of neutron computed tomography data

arXiv 2603.10947 ↗First posted 11 Mar 2026eess.IVcited by 1

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Recently, generative diffusion priors have made huge strides as inverse problem solvers, including the ability to be adapted for inference on out-of-distribution data. Concurrently, implicit neural representations (INRs) have emerged as fast and lightweight inverse imaging solvers that are amenable to hybrid approaches that combine learned priors with traditional inverse problem formulations. In this paper, we present a diffusive computed tomography (CT) inversion framework for regularizing INRs called Diffusive INR (DINR), designed to enable high-quality reconstruction from sparse-view neutron CT. Pretrained purely on synthetic data, DINR is evaluated on simulated and experimentally obtained observations of concrete microstructures, where traditional reconstruction methods suffer substantial degradation when the number of views is reduced. Our approach delivers superior performance, reduces reconstruction artifacts, and achieves gains in PSNR and SSIM, enabling accurate micro-structural characterization even under extreme data limitations compared to state-of-the-art sparse-view reconstruction techniques.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 11 of its 26 references that are in the map. First posted on arXiv 11 Mar 2026.

Builds on

11 of 26 references.

References · 11

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  4. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  6. 2018On the Spectral Bias of Neural Networkscited by 1,341
  7. 2022NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstructioncited by 108
  8. 2024Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problemscited by 21
  9. 2024Implicit Neural Representations for Robust Joint Sparse-View CT Reconstructioncited by 9
  10. 2021Algorithm-driven Advances for Scientific CT Instruments: From Model-based to Deep Learning-based Approachescited by 5
  11. 2021Sparse-View CT Reconstruction using Recurrent Stacked Back Projectioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Toward a Foundation Plug-and-Play Prior for Computed Tomography Reconstruction via a Multimodal Diffusion Modelcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024DPER: Diffusion Prior Driven Neural Representation for Limited Angle and Sparse View CT Reconstruction
  2. 2026DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction
  3. 2026Cross-Modal Guidance for Fast Diffusion-Based Computed Tomography
  4. 2024INFusion: Diffusion Regularized Implicit Neural Representations for 2D and 3D accelerated MRI reconstruction
  5. 2026Towards reconstructing experimental sparse-view X-ray CT data with diffusion models
  6. 2024Highly Accelerated MRI via Implicit Neural Representation Guided Posterior Sampling of Diffusion Models
  7. 2026From Sparse X-rays to 3D CT: Training-Free Reconstruction with Diffusion Priors
  8. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models