Our solution in competition NTIRE 2023 Bokeh Effect Transformation: https://codalab.lisn.upsaclay.fr/competitions/10229.
Download the test results from Google Drive.
Download the pretrained model from Google Drive, and place it in the folder checkpoints.
Run the following code to generate test results.
python evaluation.py --root_folder 'TEST_ROOT_FOLDER' --save_folder 'SAVE_FOLDER'
root_folder: root folder of the test dataset.save_folder: folder to save the results.
If you find our work useful in your research, please cite our paper.
@inproceedings{Peng2023Selective,
title = {Selective Bokeh Effect Transformation},
author = {Peng, Juewen and Pan, Zhiyu and Liu, Chengxin and Luo, Xianrui and Sun, Huiqiang and Shen, Liao and Xian, Ke and Cao, Zhiguo},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
year = {2023}
}