Intriguing Findings of Frequency Selection for Image Deblurring (AAAI 2023 Oral)

Xintian Mao, Yiming Liu, Fengze Liu, Qingli Li, Wei Shen and Yan Wang

Paper: https://arxiv.org/abs/2111.11745

old version: https://github.com/INVOKERer/DeepRFT

Quick Run

To test the pre-trained models of Deblur Google Drive or 百度网盘(提取码:53ph) on your own images, run

python Motion_Deblurring/val.py 

Results

Results on GoPro, HIDE, Realblur test sets: 百度网盘(提取码:mpub)

Reference Code:

• https://github.com/swz30/MPRNet
• https://github.com/chosj95/MIMO-UNet
• https://github.com/megvii-research/NAFNet
• https://github.com/megvii-research/TLC
• https://github.com/swz30/Restormer

Citation

If you use , please consider citing:

@inproceedings{xintm2023DeepRFTv2, 
    title = {Intriguing Findings of Frequency Selection for Image Deblurring},
    author = {Xintian Mao, Yiming Liu, Fengze Liu, Qingli Li, Wei Shen and Yan Wang}, 
    booktitle = {Proceedings of the 37th AAAI Conference on Artificial Intelligence}, 
    year = {2023}
    }

Contact

If you have any question, please contact [email protected]