⭐ If StarIR is helpful for you, please help star this repo. Thanks! 🤗
- 2026.04.09: 🔥 This repo is released
See INSTALL.md for the installation of dependencies required to run StarIR.
Training and Testing instructions for Deraining, Dehazing, Desnowing, Motion deblurring, Defocus deblurring, Low-light enhancement, Low-light deblurring, and all-in-one tasks are provided in their respective directories. Here is a summary table containing hyperlinkes for easy navigation.
| Task | Instructions | StarIR's Visual Results | Pre-trained Models | Datasets |
|---|---|---|---|---|
| Deraining | ||||
| Dehazing | ||||
| Desnowing | ||||
| Motion deblurring | ||||
| Defocus deblurring | ||||
| Low-light enhancement | ||||
| Low-light deblurring | ||||
| All-in-one | ||||
| UHD | [Google Drive], 百度网盘 |
|||
| CDD | [Google Drive], 百度网盘 |
To test the pre-trained StarIR models of Single_Image_Defocus_Deblurring, Dehazing, Deraining, Desnowing, Low_Light_Deblurring, Low_Light_Enhancement, and Motion_Deblurring on your own images, you can download the models, place them in the /pretrained_models/ of the corresponding tasks (e.g., ./Motion_Deblurring/pretrained_models/StarIR-GOPRO.pth), then run
python demo.py --task Task_Name --input_dir path_to_images --result_dir save_images_here
Example usage to perform Defocus Deblurring on a directory of images:
python demo.py --task Single_Image_Defocus_Deblurring --input_dir './demo/degraded/' --result_dir './demo/restored/'
Example usage to perform Defocus Deblurring on an image directly:
python demo.py --task Single_Image_Defocus_Deblurring --input_dir './demo/degraded/portrait.jpg' --result_dir './demo/restored/'
For all-in-one demo, please refer to All_in_One
Please cite us if our work is useful for your research.
@article{cui2026starir,
title={StarIR: Convolutional Image Restoration With Spatial-Frequency Fusion},
author={Cui, Yuning and Zamir, Syed Waqas and Yang, Ming-Hsuan and Knoll, Alois and Khan, Fahad Shahbaz and Khan, Salman},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2026}
}
Should you have any question, please contact yuning.cui@in.tum.de