Taming Stable Diffusion for Computed Tomography Blind Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Chunlei, Shi, Yilei, Hu, Haoxi, Hu, Jingliang, Zhu, Xiao Xiang, Mou, Lichao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916793238421504
author Li, Chunlei
Shi, Yilei
Hu, Haoxi
Hu, Jingliang
Zhu, Xiao Xiang
Mou, Lichao
author_facet Li, Chunlei
Shi, Yilei
Hu, Haoxi
Hu, Jingliang
Zhu, Xiao Xiang
Mou, Lichao
contents High-resolution computed tomography (CT) imaging is essential for medical diagnosis but requires increased radiation exposure, creating a critical trade-off between image quality and patient safety. While deep learning methods have shown promise in CT super-resolution, they face challenges with complex degradations and limited medical training data. Meanwhile, large-scale pre-trained diffusion models, particularly Stable Diffusion, have demonstrated remarkable capabilities in synthesizing fine details across various vision tasks. Motivated by this, we propose a novel framework that adapts Stable Diffusion for CT blind super-resolution. We employ a practical degradation model to synthesize realistic low-quality images and leverage a pre-trained vision-language model to generate corresponding descriptions. Subsequently, we perform super-resolution using Stable Diffusion with a specialized controlling strategy, conditioned on both low-resolution inputs and the generated text descriptions. Extensive experiments show that our method outperforms existing approaches, demonstrating its potential for achieving high-quality CT imaging at reduced radiation doses. Our code will be made publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11496
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Taming Stable Diffusion for Computed Tomography Blind Super-Resolution
Li, Chunlei
Shi, Yilei
Hu, Haoxi
Hu, Jingliang
Zhu, Xiao Xiang
Mou, Lichao
Image and Video Processing
Computer Vision and Pattern Recognition
High-resolution computed tomography (CT) imaging is essential for medical diagnosis but requires increased radiation exposure, creating a critical trade-off between image quality and patient safety. While deep learning methods have shown promise in CT super-resolution, they face challenges with complex degradations and limited medical training data. Meanwhile, large-scale pre-trained diffusion models, particularly Stable Diffusion, have demonstrated remarkable capabilities in synthesizing fine details across various vision tasks. Motivated by this, we propose a novel framework that adapts Stable Diffusion for CT blind super-resolution. We employ a practical degradation model to synthesize realistic low-quality images and leverage a pre-trained vision-language model to generate corresponding descriptions. Subsequently, we perform super-resolution using Stable Diffusion with a specialized controlling strategy, conditioned on both low-resolution inputs and the generated text descriptions. Extensive experiments show that our method outperforms existing approaches, demonstrating its potential for achieving high-quality CT imaging at reduced radiation doses. Our code will be made publicly available.
title Taming Stable Diffusion for Computed Tomography Blind Super-Resolution
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.11496