# Structure-Adaptive Sparse Diffusion in Voxel Space for 3D Medical Image Enhancement

arXiv: https://arxiv.org/abs/2604.17773 · HTML: https://mlsanity.com/paper/2604.17773/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 21 of 21)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Perception Prioritized Training of Diffusion Models](https://mlsanity.com/paper/2204.00227/) (2022)
- [Efficient Diffusion Training via Min-SNR Weighting Strategy](https://mlsanity.com/paper/2303.09556/) (2023)
- [Conditional Diffusion Models for Semantic 3D Brain MRI Synthesis](https://mlsanity.com/paper/2305.18453/) (2023)
- [PET image denoising based on denoising diffusion probabilistic models](https://mlsanity.com/paper/2209.06167/) (2022)
- [WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis](https://mlsanity.com/paper/2402.19043/) (2024)
- [CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization](https://mlsanity.com/paper/2304.01814/) (2023)
- [Make-A-Volume: Leveraging Latent Diffusion Models for Cross-Modality 3D Brain MRI Synthesis](https://mlsanity.com/paper/2307.10094/) (2023)
- [Addressing Negative Transfer in Diffusion Models](https://mlsanity.com/paper/2306.00354/) (2023)
- [Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image Generation](https://mlsanity.com/paper/2405.14802/) (2024)
- [Memory-Efficient 3D Denoising Diffusion Models for Medical Image Processing](https://mlsanity.com/paper/2303.15288/) (2023)
- [Diffusion Probabilistic Priors for Zero-Shot Low-Dose CT Image Denoising](https://mlsanity.com/paper/2305.15887/) (2023)
- [SOUP-GAN: Super-Resolution MRI Using Generative Adversarial Networks](https://mlsanity.com/paper/2106.02599/) (2021)
- [Brain MRI super-resolution using 3D generative adversarial networks](https://mlsanity.com/paper/1812.11440/) (2018)
- [Memory-efficient GAN-based Domain Translation of High Resolution 3D Medical Images](https://mlsanity.com/paper/2010.03396/) (2020)
- [PixelGen: Improving Pixel Diffusion with Perceptual Supervision](https://mlsanity.com/paper/2602.02493/) (2026)
- [Multi-Class Segmentation of Aortic Branches and Zones in Computed Tomography Angiography: The AortaSeg24 Challenge](https://mlsanity.com/paper/2502.05330/) (2025)
- [Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning](https://mlsanity.com/paper/2410.06664/) (2024)
- [3D Wavelet Latent Diffusion Model for Whole-Body MR-to-CT Modality Translation](https://mlsanity.com/paper/2507.11557/) (2025)

## Abstract (arXiv)

Three-dimensional (3D) medical image enhancement, including denoising and super-resolution, is critical for clinical diagnosis in CT, PET, and MRI. Although diffusion models have shown remarkable success in 2D medical imaging, scaling them to high-resolution 3D volumes remains computationally prohibitive due to lengthy diffusion trajectories over high-dimensional volumetric data. We observe that in conditional enhancement, strong anatomical priors in the degraded input render dense noise schedules largely redundant. Leveraging this insight, we propose a sparse voxel-space diffusion framework that trains and samples on a compact set of uniformly subsampled timesteps. The network predicts clean data directly on the data manifold, supervised in velocity space for stable gradient scaling. A lightweight Structure-aware Trajectory Modulation (STM) module recalibrates time embeddings at each network block based on local anatomical content, enabling structure-adaptive denoising over the shared sparse schedule. Operating directly in voxel space, our framework preserves fine anatomical detail without lossy compression while achieving up to 10× training acceleration. Experiments on four datasets spanning CT, PET, and MRI demonstrate state-of-the-art performance on both denoising and super-resolution tasks. Our code is publicly available at: https://github.com/mirthAI/sparse-3d-diffusion.