{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/wdm-3d-wavelet-diffusion-models-for-high","title":"WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis","arxiv_id":"2402.19043","date":"2024-02-29","proceeding":null,"authors":["Paul Friedrich","Julia Wolleb","Florentin Bieder","Alicia Durrer","Philippe C. Cattin"],"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 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 $128 \\times 128 \\times 128$ 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 $256 \\times 256 \\times 256$, outperforming all comparing methods.","url_abs":"https://arxiv.org/abs/2402.19043v2","url_pdf":"https://arxiv.org/pdf/2402.19043v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"wdm-3d-wavelet-diffusion-models-for-high","repo_url":"https://github.com/pfriedri/wdm-3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"medical-image-generation","task_name":"Medical Image Generation"},{"task_slug":"unconditional-image-generation","task_name":"Unconditional Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.19043","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}