Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models

About

Diffusion models have become a popular approach for image generation and reconstruction due to their numerous advantages. However, most diffusion-based inverse problem-solving methods only deal with 2D images, and even recently published 3D methods do not fully exploit the 3D distribution prior. To address this, we propose a novel approach using two perpendicular pre-trained 2D diffusion models to solve the 3D inverse problem. By modeling the 3D data distribution as a product of 2D distributions sliced in different directions, our method effectively addresses the curse of dimensionality. Our experimental results demonstrate that our method is highly effective for 3D medical image reconstruction tasks, including MRI Z-axis super-resolution, compressed sensing MRI, and sparse-view CT. Our method can generate high-quality voxel volumes suitable for medical applications.

Suhyeon Lee, Hyungjin Chung, Minyoung Park, Jonghyuk Park, Wi-Sun Ryu, Jong Chul Ye• 2023

Related benchmarks

TaskDatasetResultRank
Sparse-View CT ReconstructionLIDC Coronal View (test)
PSNR28.12
24
Sparse-View CT ReconstructionLIDC Sagittal View (test)
PSNR27.66
24
Sparse-View CT ReconstructionLIDC
PSNR27.51
24
Sparse-View Computed Tomography (SVCT)AAPM low-dose CT 2016 (Patient L506)
Axial PSNR37.59
11
Limited-Angle CT ReconstructionLIDC Axial
PSNR14.44
8
Limited-Angle CT ReconstructionLIDC Sagittal
PSNR14.06
8
Limited-Angle CT ReconstructionLIDC Coronal
PSNR14.54
8
LACT reconstructionLACT Subject L506 1mm 1.0 (test)
PSNR (Axial)30.95
4
Showing 8 of 8 rows

Other info

Follow for update