Improving 2D Diffusion Models for 3D Medical Imaging with Inter-Slice Consistent Stochasticity

• URL: http://arxiv.org/abs/2602.04162v2
• Date: Mon, 09 Feb 2026 14:41:08 GMT
• Title: Improving 2D Diffusion Models for 3D Medical Imaging with Inter-Slice Consistent Stochasticity
• Authors: Chenhe Du, Qing Wu, Xuanyu Tian, Jingyi Yu, Hongjiang Wei, Yuyao Zhang,
• Abstract summary: Inter-Slice Consistentity (ISCS) is a strategy that encourages interslice consistency during diffusion sampling.<n>ISCS can be dropped into any 2D trained diffusion based 3D reconstruction pipeline without additional computational cost.
• Score: 47.52394044948656
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 3D medical imaging is in high demand and essential for clinical diagnosis and scientific research. Currently, diffusion models (DMs) have become an effective tool for medical imaging reconstruction thanks to their ability to learn rich, high-quality data priors. However, learning the 3D data distribution with DMs in medical imaging is challenging, not only due to the difficulties in data collection but also because of the significant computational burden during model training. A common compromise is to train the DMs on 2D data priors and reconstruct stacked 2D slices to address 3D medical inverse problems. However, the intrinsic randomness of diffusion sampling causes severe inter-slice discontinuities of reconstructed 3D volumes. Existing methods often enforce continuity regularizations along the z-axis, which introduces sensitive hyper-parameters and may lead to over-smoothing results. In this work, we revisit the origin of stochasticity in diffusion sampling and introduce Inter-Slice Consistent Stochasticity (ISCS), a simple yet effective strategy that encourages interslice consistency during diffusion sampling. Our key idea is to control the consistency of stochastic noise components during diffusion sampling, thereby aligning their sampling trajectories without adding any new loss terms or optimization steps. Importantly, the proposed ISCS is plug-and-play and can be dropped into any 2D trained diffusion based 3D reconstruction pipeline without additional computational cost. Experiments on several medical imaging problems show that our method can effectively improve the performance of medical 3D imaging problems based on 2D diffusion models. Our findings suggest that controlling inter-slice stochasticity is a principled and practically attractive route toward high-fidelity 3D medical imaging with 2D diffusion priors. The code is available at: https://github.com/duchenhe/ISCS

Related papers

• PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior [5.104613802755622]
  We introduce a Plugand-play algorithm for 3D inference with latent diffusion prior (PSI3D)<n>Specifically, we formulate a Markov chain Monte Carlo approach to reconstruct each two-dimensional (2D) slice by sampling from a 2D latent diffusion model.
  arXiv  Detail & Related papers  (2025-12-20T13:37:22Z)
• Introducing 3D Representation for Medical Image Volume-to-Volume Translation via Score Fusion [3.3559609260669303]
  We present Score-Fusion, a novel volumetric translation model that effectively learns 3D representations by ensembling perpendicularly trained 2D diffusion models in score function space.<n>We show that Score-Fusion achieves superior accuracy and volumetric fidelity in 3D medical image super-resolution and modality translation.
  arXiv  Detail & Related papers  (2025-01-13T15:54:21Z)
• Zero-1-to-G: Taming Pretrained 2D Diffusion Model for Direct 3D Generation [66.75243908044538]
  We introduce Zero-1-to-G, a novel approach to direct 3D generation on Gaussian splats using pretrained 2D diffusion models.<n>To incorporate 3D awareness, we introduce cross-view and cross-attribute attention layers, which capture complex correlations and enforce 3D consistency across generated splats.<n>This makes Zero-1-to-G the first direct image-to-3D generative model to effectively utilize pretrained 2D diffusion priors, enabling efficient training and improved generalization to unseen objects.
  arXiv  Detail & Related papers  (2025-01-09T18:37:35Z)
• Resolution-Robust 3D MRI Reconstruction with 2D Diffusion Priors: Diverse-Resolution Training Outperforms Interpolation [18.917672392645006]
  2D diffusion models trained on 2D slices are starting to be leveraged for 3D MRI reconstruction.<n>Existing methods pertain to a fixed voxel size, and performance degrades when the voxel size is varied.<n>We propose and study several approaches for resolution-robust 3D MRI reconstruction with 2D diffusion priors.
  arXiv  Detail & Related papers  (2024-12-24T18:25:50Z)
• DSplats: 3D Generation by Denoising Splats-Based Multiview Diffusion Models [67.50989119438508]
  We introduce DSplats, a novel method that directly denoises multiview images using Gaussian-based Reconstructors to produce realistic 3D assets.<n>Our experiments demonstrate that DSplats not only produces high-quality, spatially consistent outputs, but also sets a new standard in single-image to 3D reconstruction.
  arXiv  Detail & Related papers  (2024-12-11T07:32:17Z)
• DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction [12.04892150473192]
  We propose a novel framework that enables learning the 3D image prior through position-aware 3D-patch diffusion score blending. Our algorithm also comes with better or comparable computational efficiency than previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-06-14T17:47:50Z)
• Generative Enhancement for 3D Medical Images [74.17066529847546]
  We propose GEM-3D, a novel generative approach to the synthesis of 3D medical images. Our method begins with a 2D slice, noted as the informed slice to serve the patient prior, and propagates the generation process using a 3D segmentation mask. By decomposing the 3D medical images into masks and patient prior information, GEM-3D offers a flexible yet effective solution for generating versatile 3D images.
  arXiv  Detail & Related papers  (2024-03-19T15:57:04Z)
• Make-A-Volume: Leveraging Latent Diffusion Models for Cross-Modality 3D Brain MRI Synthesis [35.45013834475523]
  Cross-modality medical image synthesis is a critical topic and has the potential to facilitate numerous applications in the medical imaging field. Most current medical image synthesis methods rely on generative adversarial networks and suffer from notorious mode collapse and unstable training. We introduce a new paradigm for volumetric medical data synthesis by leveraging 2D backbones and present a diffusion-based framework, Make-A-Volume.
  arXiv  Detail & Related papers  (2023-07-19T16:01:09Z)
• Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models [52.529394863331326]
  We propose a novel approach using two perpendicular pre-trained 2D diffusion models to solve the 3D inverse problem. Our method is highly effective for 3D medical image reconstruction tasks, including MRI Z-axis super-resolution, compressed sensing MRI, and sparse-view CT.
  arXiv  Detail & Related papers  (2023-03-15T08:28:06Z)
• DreamFusion: Text-to-3D using 2D Diffusion [52.52529213936283]
  Recent breakthroughs in text-to-image synthesis have been driven by diffusion models trained on billions of image-text pairs. In this work, we circumvent these limitations by using a pretrained 2D text-to-image diffusion model to perform text-to-3D synthesis. Our approach requires no 3D training data and no modifications to the image diffusion model, demonstrating the effectiveness of pretrained image diffusion models as priors.
  arXiv  Detail & Related papers  (2022-09-29T17:50:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.