|
--- |
|
license: mit |
|
language: |
|
- en |
|
tags: |
|
- 3d |
|
- medical |
|
- image-synthesis |
|
- image-generation |
|
- wavelet-transform |
|
arxiv: 2402.19043 |
|
--- |
|
|
|
# WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis |
|
This is the officical model repository of the paper "[**WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis**](https://pfriedri.github.io/wdm-3d-io)" by Paul Friedrich, Julia Wolleb, Florentin Bieder, Alicia Durrer and Philippe C. Cattin. |
|
|
|
**WDM** is a wavelet-based medical image synthesis framework that can generate high-resolution medical images like CT or MR scans. |
|
For more information on our method, we refer to our [**project page**](https://pfriedri.github.io/wdm-3d-io) or the [**paper**](https://arxiv.org/abs/2402.19043). |
|
|
|
## Origial GitHub repository |
|
If you want to use the pre-trained models provided in this repository, download the model weights and follow the instructions in the official [GitHub repository](https://github.com/pfriedri/wdm-3d). |
|
|
|
## Pre-trained models |
|
We will soon provide models for different datasets and different image resolutions (starting with BraTs and LIDC-IDRI at resolutions of 128³ and 256³). |
|
|
|
## Hardware requirements |
|
To sample images from the provided models, you require a GPU with at least: |
|
- 3 GB VRAM - for 128 x 128 x 128 (model uses ~2.55 GB) |
|
- 8 GB VRAM - for 256 x 256 x 256 (model uses ~7.27 GB) |
|
|
|
The models were trained on a system with an an AMD Epyc 7742 CPU and a NVIDIA A100 (40GB) GPU. |
|
|
|
## Citation |
|
If you find this work useful, please cite: |
|
```bibtex |
|
@article{friedrich2024wdm, |
|
title={WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis}, |
|
author={Paul Friedrich and Julia Wolleb and Florentin Bieder and Alicia Durrer and Philippe C. Cattin}, |
|
year={2024}, |
|
journal={arXiv preprint arXiv:2402.19043}} |
|
``` |
