mlsanityData to 7 Oct 2026

Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models

arXiv 2303.08440 ↗First posted 15 Mar 2023eess.IV cs.CV cs.LGcited by 53

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Diffusion models have become a popular approach for image generation and reconstruction due to their numerous advantages. However, most diffusion-based inverse problem-solving methods only deal with 2D images, and even recently published 3D methods do not fully exploit the 3D distribution prior. To address this, we propose a novel approach using two perpendicular pre-trained 2D diffusion models to solve the 3D inverse problem. By modeling the 3D data distribution as a product of 2D distributions sliced in different directions, our method effectively addresses the curse of dimensionality. Our experimental results demonstrate that our method is highly effective for 3D medical image reconstruction tasks, including MRI Z-axis super-resolution, compressed sensing MRI, and sparse-view CT. Our method can generate high-quality voxel volumes suitable for medical applications.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 36 of its 50 references that are in the map. First posted on arXiv 15 Mar 2023.

Builds on

36 of 50 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models19 Nov
  2. 2022Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding13 Nov
  3. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Models15 Nov
  4. 2021Score-based diffusion models for accelerated MRI8 Oct

Other references · 32

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  11. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  12. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
20 more
  1. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  2. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  3. 2022Denoising Diffusion Restoration Modelscited by 951
  4. 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 673
  5. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
  6. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  7. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 503
  8. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 501
  9. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  10. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
  11. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  12. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  13. 2023Dreamix: Video Diffusion Models are General Video Editorscited by 189
  14. 2022FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesiscited by 136
  15. 2022Parallel Diffusion Models of Operator and Image for Blind Inverse Problemscited by 113
  16. 2021Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Imagescited by 110
  17. 2020DuDoRNet: Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction with Deep T1 Priorcited by 72
  18. 2022GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generationcited by 43
  19. 2022Surface Vision Transformers: Attention-Based Modelling applied to Cortical Analysiscited by 25
  20. 2022Sparse-view Cone Beam CT Reconstruction using Data-consistent Supervised and Adversarial Learning from Scarce Training Datacited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 20; 2025: 12; 2026: 13.

53 papers.

Sort:

By area:

  1. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistencycited by 180
  2. 2023Prompt-tuning latent diffusion models for inverse problemscited by 70
  3. 2024R2-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstructioncited by 65
  4. 2023Make-A-Volume: Leveraging Latent Diffusion Models for Cross-Modality 3D Brain MRI Synthesiscited by 43
  5. 2023Regularization by Texts for Latent Diffusion Inverse Solverscited by 31
  6. 2024Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problemscited by 21
  7. 2024Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problemscited by 18
  8. 2025Diffusion models for inverse problemscited by 15
  9. 2024Deep Generative Models for 3D Medical Image Synthesiscited by 14
  10. 20242.5D Multi-view Averaging Diffusion Model for 3D Medical Image Translation: Application to Low-count PET Reconstruction with CT-less Attenuation Correctioncited by 13
  11. 2024DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstructioncited by 13
  12. 2023DDPET-3D: Dose-aware Diffusion Model for 3D Ultra Low-dose PET Imagingcited by 12
38 more
  1. 2023A Survey of Emerging Applications of Diffusion Probabilistic Models in MRIcited by 9
  2. 2024Cascaded Multi-path Shortcut Diffusion Model for Medical Image Translationcited by 9
  3. 2024DiffuX2CT: Diffusion Learning to Reconstruct CT Images from Biplanar X-Rayscited by 9
  4. 2024Likelihood-Scheduled Score-Based Generative Modeling for Fully 3D PET Image Reconstructioncited by 9
  5. 2024DIFR3CT: Latent Diffusion for Probabilistic 3D CT Reconstruction from Few Planar X-Rayscited by 8
  6. 2025Regression is all you need for medical image translationcited by 8
  7. 2025X2-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstructioncited by 6
  8. 2023Two-and-a-half Order Score-based Model for Solving 3D Ill-posed Inverse Problemscited by 5
  9. 2024X-Diffusion: Generating Detailed 3D MRI Volumes From a Single Image Using Cross-Sectional Diffusion Modelscited by 5
  10. 2024Dose-aware Diffusion Model for 3D PET Image Denoising: Multi-institutional Validation with Reader Study and Real Low-dose Datacited by 5
  11. 2024Physics-Inspired Generative Models in Medical Imaging: A Reviewcited by 5
  12. 2025X-LRM: X-ray Large Reconstruction Model for Extremely Sparse-View Computed Tomography Recovery in One Secondcited by 5
  13. 2025X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomographycited by 5
  14. 2025GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstructioncited by 5
  15. 2024Blaze3DM: Marry Triplane Representation with Diffusion for 3D Medical Inverse Problem Solvingcited by 4
  16. 2023Data-iterative Optimization Score Model for Stable Ultra-Sparse-View CT Reconstructioncited by 3
  17. 2024Super-resolution of biomedical volumes with 2D supervisioncited by 3
  18. 2024Reference-free Axial Super-resolution of 3D Microscopy Images using Implicit Neural Representation with a 2D Diffusion Priorcited by 3
  19. 2024Swap-Net: A Memory-Efficient 2.5D Network for Sparse-View 3D Cone Beam CT Reconstructioncited by 3
  20. 2026Improving 2D Diffusion Models for 3D Medical Imaging with Inter-Slice Consistent Stochasticitycited by 3
  21. 2025Bigger Isn't Always Better: Towards a General Prior for Medical Image Reconstructioncited by 2
  22. 2025From 2D to 3D, Deep Learning-based Shape Reconstruction in Magnetic Resonance Imaging: A Reviewcited by 2
  23. 2024Intensity Field Decomposition for Tissue-Guided Neural Tomographycited by 1
  24. 2024Resolution-Robust 3D MRI Reconstruction with 2D Diffusion Priors: Diverse-Resolution Training Outperforms Interpolationcited by 1
  25. 2025Local Patches Meet Global Context: Scalable 3D Diffusion Priors for Computed Tomography Reconstructioncited by 1
  26. 2026Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstructioncited by 1
  27. 2024From Diffusion to Resolution: Leveraging 2D Diffusion Models for 3D Super-Resolution Taskcited by 0
  28. 2025Efficient and robust 3D blind harmonization for large domain gapscited by 0
  29. 2025Latent Space Consistency for Sparse-View CT Reconstructioncited by 0
  30. 2025MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomographycited by 0
  31. 2026TG-Field: Geometry-Aware Radiative Gaussian Fields for Tomographic Reconstructioncited by 0
  32. 20263D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problemscited by 0
  33. 20263D CBCT Artefact Removal Using Perpendicular Score-Based Diffusion Modelscited by 0
  34. 2026ILV: Iterative Latent Volumes for Fast and Accurate Sparse-View CT Reconstructioncited by 0
  35. 2026Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstructioncited by 0
  36. 2026MK-ResRecon: Multi-Kernel Residual Framework for Texture-Aware 3D MRI Refinement from Sparse 2D Slicescited by 0
  37. 2026GeoTopoDiff: Learning Geometry--Topology Graph Priors through Boundary-Constrained Mixed Diffusion for Sparse-Slice 3D Porous Reconstructioncited by 0
  38. 2026SkelEM: Training-Signal Decoupling of Skeleton and Diffusion for Self-supervised Axial Super-Resolution in Volume Microscopycited by 0

50 most cited of 53 All 53 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025NERD: Network-Regularized Diffusion Sampling For 3D Computed Tomography
  2. 2024A Survey on Diffusion Models for Inverse Problems
  3. 2026From Sparse X-rays to 3D CT: Training-Free Reconstruction with Diffusion Priors
  4. 2026Scale-Cascaded Diffusion Models for Super-Resolution in Medical Imaging
  5. 2026DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstruction
  6. 2024MRI Reconstruction with Regularized 3D Diffusion Model (R3DM)
  7. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction
  8. 2023Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models