0

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

A novel approach using two perpendicular pre-trained 2D diffusion models solves 3D inverse problems effectively for medical image reconstruction tasks.

Year
2023
Venue
ICCV 2023 1
Authors
6
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2303.08440v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

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.

Authors

6