mlsanityData to 7 Oct 2026

PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior

arXiv 2512.18367 ↗First posted 20 Dec 2025eess.IV cs.LGcited by 3

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Diffusion models are highly expressive image priors for Bayesian inverse problems. However, most diffusion models cannot operate on large-scale, high-dimensional data due to high training and inference costs. In this work, we introduce a Plug-and-play algorithm for 3D stochastic inference with latent diffusion prior (PSI3D) to address massive (1024× 1024× 128) volumes. Specifically, we formulate a Markov chain Monte Carlo approach to reconstruct each two-dimensional (2D) slice by sampling from a 2D latent diffusion model. To enhance inter-slice consistency, we also incorporate total variation (TV) regularization stochastically along the concatenation axis. We evaluate our performance on optical coherence tomography (OCT) super-resolution. Our method significantly improves reconstruction quality for large-scale scientific imaging compared to traditional and learning-based baselines, while providing robust and credible reconstructions.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 28 of its 43 references that are in the map. First posted on arXiv 20 Dec 2025.

Builds on

28 of 43 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Super-Resolution Optical Coherence Tomography Using Diffusion Model-Based Plug-and-Play Priors20 May
  2. 2024Iterative CT Reconstruction via Latent Variable Optimization of Shallow Diffusion Models6 Aug
  3. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models19 Nov

Other references · 25

  1. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  4. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  7. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  8. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  9. 2016Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applicationscited by 244
  10. 2019Plug-and-Play Methods Provably Converge with Properly Trained Denoiserscited by 197
  11. 2023Score-Based Diffusion Models as Principled Priors for Inverse Imagingcited by 126
  12. 2022Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imagingcited by 94
13 more
  1. 2024Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priorscited by 93
  2. 2019Plug and play methods for magnetic resonance imaging (long version)cited by 75
  3. 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstructioncited by 73
  4. 2017Plug-and-Play Unplugged: Optimization Free Reconstruction using Consensus Equilibriumcited by 58
  5. 2023Provable Probabilistic Imaging using Score-Based Generative Priorscited by 51
  6. 2020Scalable Plug-and-Play ADMM with Convergence Guaranteescited by 49
  7. 2018Split-and-augmented Gibbs sampler - Application to large-scale inference problemscited by 47
  8. 2013Proximal Markov chain Monte Carlo algorithmscited by 46
  9. 2017Sampling from a log-concave distribution with compact support with proximal Langevin Monte Carlocited by 43
  10. 2023Plug-and-Play split Gibbs sampler: embedding deep generative priors in Bayesian inferencecited by 41
  11. 2023Generative Plug and Play: Posterior Sampling for Inverse Problemscited by 24
  12. 2020Multi-Slice Fusion for Sparse-View and Limited-Angle 4D CT Reconstructioncited by 9
  13. 2020Efficient and high accuracy 3-D OCT angiography motion correction in pathologycited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026End-to-end reconstruction of OCT optical properties and speckle-reduced structural intensity via physics-based learningcited by 0
  2. 2026Physics-based generation of multilayer corneal OCT data via Gaussian modeling and MCML for AI-driven diagnostic and surgical guidance applicationscited by 0
  3. 2026Super-Resolution and Denoising of Corneal B-Scan OCT Imaging Using Diffusion Model Plug-and-Play Priorscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Improving 2D Diffusion Models for 3D Medical Imaging with Inter-Slice Consistent Stochasticity
  2. 2025Consistency Diffusion Models for Single-Image 3D Reconstruction with Priors
  3. 2024DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction
  4. 2025Local Patches Meet Global Context: Scalable 3D Diffusion Priors for Computed Tomography Reconstruction
  5. 2026Patch-PODiff-ViT: Structured Latent Diffusion with Patchwise POD for Super-Resolution and Uncertainty Quantification
  6. 2024Resolution-Robust 3D MRI Reconstruction with 2D Diffusion Priors: Diverse-Resolution Training Outperforms Interpolation
  7. 2025Physics-Guided Diffusion Priors for Multi-Slice Reconstruction in Scientific Imaging
  8. 2023Variational Bayesian Imaging with an Efficient Surrogate Score-based Prior