{"ID":2890764,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.18112","arxiv_id":"2507.18112","title":"Parameter-Efficient Fine-Tuning of 3D DDPM for MRI Image Generation Using Tensor Networks","abstract":"We address the challenge of parameter-efficient fine-tuning (PEFT) for three-dimensional (3D) U-Net-based denoising diffusion probabilistic models (DDPMs) in magnetic resonance imaging (MRI) image generation. Despite its practical significance, research on parameter-efficient representations of 3D convolution operations remains limited. To bridge this gap, we propose Tensor Volumetric Operator (TenVOO), a novel PEFT method specifically designed for fine-tuning DDPMs with 3D convolutional backbones. Leveraging tensor network modeling, TenVOO represents 3D convolution kernels with lower-dimensional tensors, effectively capturing complex spatial dependencies during fine-tuning with few parameters. We evaluate TenVOO on three downstream brain MRI datasets-ADNI, PPMI, and BraTS2021-by fine-tuning a DDPM pretrained on 59,830 T1-weighted brain MRI scans from the UK Biobank. Our results demonstrate that TenVOO achieves state-of-the-art performance in multi-scale structural similarity index measure (MS-SSIM), outperforming existing approaches in capturing spatial dependencies while requiring only 0.3% of the trainable parameters of the original model. Our code is available at: https://github.com/xiaovhua/tenvoo","short_abstract":"We address the challenge of parameter-efficient fine-tuning (PEFT) for three-dimensional (3D) U-Net-based denoising diffusion probabilistic models (DDPMs) in magnetic resonance imaging (MRI) image generation. Despite its practical significance, research on parameter-efficient representations of 3D convolution operation...","url_abs":"https://arxiv.org/abs/2507.18112","url_pdf":"https://arxiv.org/pdf/2507.18112v1","authors":"[\"Binghua Li\",\"Ziqing Chang\",\"Tong Liang\",\"Chao Li\",\"Toshihisa Tanaka\",\"Shigeki Aoki\",\"Qibin Zhao\",\"Zhe Sun\"]","published":"2025-07-24T05:51:51Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.AI\",\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":611809,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2890764,"paper_url":"https://arxiv.org/abs/2507.18112","paper_title":"Parameter-Efficient Fine-Tuning of 3D DDPM for MRI Image Generation Using Tensor Networks","repo_url":"https://github.com/xiaovhua/tenvoo","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}