WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis
CoRR(2024)
Abstract
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 diffusion models to high resolutions and can be trained on a
single 40 GB GPU. Experimental results on BraTS and LIDC-IDRI unconditional
image generation at a resolution of 128 × 128 × 128 show
state-of-the-art image fidelity (FID) and sample diversity (MS-SSIM) scores
compared to 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.
MoreTranslated text
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined