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

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

15 Mar 2023ICCV 2023 1arXiv:2303.08440archive 2025-07-28

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

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

hyn2028/tpdm officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image GenerationImage ReconstructionMedical Image EnhancementSuper-Resolutioncompressed sensing

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Denoising Score MatchingDiffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections