This repository is a curated list of research papers on diffusion models applied to low-level vision tasks. It serves as a comprehensive resource for researchers and practitioners interested in leveraging diffusion models for image restoration, enhancement, and generation in areas like natural images, medical imaging, and remote sensing.

How It Works

The repository categorizes diffusion model papers based on their application in low-level vision. It covers general image restoration, task-specific applications (super-resolution, inpainting, deblurring, dehazing, low-light enhancement, image fusion), and extended applications in medical imaging and remote sensing. The structure allows users to quickly find relevant research and understand the landscape of diffusion models in these domains.

Quick Start & Requirements

This is a curated list of papers and does not have a direct installation or execution command. Users will need to access the linked papers and their associated code repositories for practical implementation.

Highlighted Details

• Extensive categorization of diffusion models across various low-level vision tasks.
• Includes links to papers, code, and relevant datasets for each entry.
• Features a dedicated section for diffusion models in medical imaging and remote sensing.
• Provides links to related surveys and large-scale datasets for model pre-training.

Maintenance & Community

The repository is maintained by ChunmingHe and welcomes contributions via Issues and pull requests. It was last updated on February 24, 2025.

Licensing & Compatibility

The repository itself is a list of links and does not impose a specific license. Individual papers and their associated code will have their own licenses.

Limitations & Caveats

As a curated list, the repository's value is dependent on the accuracy and completeness of the included papers and their links. It does not provide direct implementations or pre-trained models.