[CVPR-2025] GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration
Sudarshan Rajagopalan | Nithin Gopalakrishnan Nair | Jay N. Paranjape| Vishal M. Patel
For instructions regarding training and inference of the GenDeg model refer to this file.
To download the GenDS dataset please refer to the dataset page.
- GenDS dataset
- GenDeg inference
- GenDeg training
- Restoration inference
- Restoration training
- Pre-trained models
If you found our work useful, please consider citing:
@article{rajagopalan2024gendeg,
title={GenDeg: Diffusion-Based Degradation Synthesis for Generalizable All-in-One Image Restoration},
author={Rajagopalan, Sudarshan and Nair, Nithin Gopalakrishnan and Paranjape, Jay N and Patel, Vishal M},
journal={arXiv preprint arXiv:2411.17687},
year={2024}
}