mlsanityData to 7 Oct 2026

DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction

arXiv 2406.10211 ↗First posted 14 Jun 2024cs.CVcited by 13

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Diffusion models face significant challenges when employed for large-scale medical image reconstruction in real practice such as 3D Computed Tomography (CT). Due to the demanding memory, time, and data requirements, it is difficult to train a diffusion model directly on the entire volume of high-dimensional data to obtain an efficient 3D diffusion prior. Existing works utilizing diffusion priors on single 2D image slice with hand-crafted cross-slice regularization would sacrifice the z-axis consistency, which results in severe artifacts along the z-axis. In this work, we propose a novel framework that enables learning the 3D image prior through position-aware 3D-patch diffusion score blending for reconstructing large-scale 3D medical images. To the best of our knowledge, we are the first to utilize a 3D-patch diffusion prior for 3D medical image reconstruction. Extensive experiments on sparse view and limited angle CT reconstruction show that our DiffusionBlend method significantly outperforms previous methods and achieves state-of-the-art performance on real-world CT reconstruction problems with high-dimensional 3D image (i.e., 256 × 256 × 500). Our algorithm also comes with better or comparable computational efficiency than previous state-of-the-art methods.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 39 of its 55 references that are in the map. First posted on arXiv 14 Jun 2024.

Builds on

39 of 55 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Parallel Diffusion Model-based Sparse-view Cone-beam Breast CT22 Mar
  2. 2023Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models15 Mar
  3. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models19 Nov
  4. 2022Patch-Based Denoising Diffusion Probabilistic Model for Sparse-View CT Reconstruction18 Nov
  5. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Models15 Nov

Other references · 34

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  8. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  9. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  10. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  11. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  12. 2022Denoising Diffusion Restoration Modelscited by 951
22 more
  1. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
  2. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 501
  3. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
  4. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
  5. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  6. 2023I2SB: Image-to-Image Schr"odinger Bridgecited by 214
  7. 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 211
  8. 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
  9. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistencycited by 180
  10. 2023Video Probabilistic Diffusion Models in Projected Latent Spacecited by 171
  11. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
  12. 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problemscited by 129
  13. 2017Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CTcited by 87
  14. 2018Image Restoration using Total Variation Regularized Deep Image Priorcited by 65
  15. 2023Direct Diffusion Bridge using Data Consistency for Inverse Problemscited by 65
  16. 2023Monte Carlo guided Diffusion for Bayesian linear inverse problemscited by 65
  17. 2024VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Modelscited by 56
  18. 2020Provable Convergence of Plug-and-Play Priors with MMSE denoiserscited by 39
  19. 2022Online Deep Equilibrium Learning for Regularization by Denoisingcited by 22
  20. 2022Sparse-view Cone Beam CT Reconstruction using Data-consistent Supervised and Adversarial Learning from Scarce Training Datacited by 17
  21. 2020Boosting the Performance of Plug-and-Play Priors via Denoiser Scalingcited by 12
  22. 2022CoRRECT: A Deep Unfolding Framework for Motion-Corrected Quantitative R2* Mappingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 6; 2026: 4.

13 papers.

Sort:

By area:

  1. 2024Patch-Based Diffusion Models Beat Whole-Image Models for Mismatched Distribution Inverse Problemscited by 8
  2. 2025Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinementcited by 6
  3. 2025VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesiscited by 6
  4. 2026Improving 2D Diffusion Models for 3D Medical Imaging with Inter-Slice Consistent Stochasticitycited by 3
  5. 2024Iterative CT Reconstruction via Latent Variable Optimization of Shallow Diffusion Modelscited by 1
  6. 2024Resolution-Robust 3D MRI Reconstruction with 2D Diffusion Priors: Diverse-Resolution Training Outperforms Interpolationcited by 1
  7. 2025Local Patches Meet Global Context: Scalable 3D Diffusion Priors for Computed Tomography Reconstructioncited by 1
  8. 2025GriDiT: Factorized Grid-Based Diffusion for Efficient Long Image Sequence Generationcited by 1
  9. 2025Efficient and robust 3D blind harmonization for large domain gapscited by 0
  10. 2025Resolution-Agnostic Neural Operators for Multi-Rate Sparse-View CTcited by 0
  11. 20263D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problemscited by 0
  12. 2026GeoTopoDiff: Learning Geometry--Topology Graph Priors through Boundary-Constrained Mixed Diffusion for Sparse-Slice 3D Porous Reconstructioncited by 0
1 more
  1. 2026Tracing the Oracle: Improving Diffusion Timestep Scheduling for 3D CT Reconstructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025When are Diffusion Priors Helpful in Sparse Reconstruction? A Study with Sparse-view CT
  2. 2024Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problems
  3. 2025Ordered-subsets Multi-diffusion Model for Sparse-view CT Reconstruction
  4. 2026DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction
  5. 2026DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstruction
  6. 2026Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstruction
  7. 2023CT Reconstruction using Diffusion Posterior Sampling conditioned on a Nonlinear Measurement Model
  8. 2025NERD: Network-Regularized Diffusion Sampling For 3D Computed Tomography