Papers › WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis

WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis

29 Feb 2024arXiv:2402.19043archive 2025-07-28

Paul Friedrich, Julia Wolleb, Florentin Bieder, Alicia Durrer, Philippe C. Cattin

Due to the three-dimensional nature of CT- or MR-scans, generative modeling of medical images is a particularly challenging task. Existing approaches mostly apply patch-wise, slice-wise, or cascaded generation techniques to fit the high-dimensional data into the limited GPU memory. However, these approaches may introduce artifacts and potentially restrict the model's applicability for certain downstream tasks. This work presents WDM, a wavelet-based medical image synthesis framework that applies a diffusion model on wavelet decomposed images. The presented approach is a simple yet effective way of scaling 3D diffusion models to high resolutions and can be trained on a single \SI{40}{\giga\byte} GPU. Experimental results on BraTS and LIDC-IDRI unconditional image generation at a resolution of 128 ×128 ×128 demonstrate state-of-the-art image fidelity (FID) and sample diversity (MS-SSIM) scores compared to recent GANs, Diffusion Models, and Latent Diffusion Models. Our proposed method is the only one capable of generating high-quality images at a resolution of 256 ×256 ×256, outperforming all comparing methods.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

pfriedri/wdm-3d officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DiversityImage GenerationMedical Image GenerationUnconditional Image Generation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections