The implementation of CVPR 2019 paper "Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements"
News (19/09/2019): Fix the broken link; our pretrained model and collected unaligned dataset are now available at OneDrive
7,643 cropped images with size 224 × 224 from Pascal VOC dataset (image ids are provided in VOC2012_224_train_png.txt, you should crop the center region with size 224 x 224 to reproduce our result).
90 real-world training images from Berkeley real dataset
Once the data are downloaded, you must organize the dataset according to our code implementation (see the source code of datasets.CEILDataset, e.t.c.)
errnet_060_00463920.pt
to checkpoints/errnet/
. python test_errnet.py --name errnet -r --icnn_path checkpoints/errnet/errnet_060_00463920.pt --hyper
python train_errnet.py --name errnet --hyper
options/errnet/train_options.py
to see more training options. python train_errnet_unaligned.py --name errnet_unaligned_ft --hyper -r --icnn_path checkpoints/errnet/errnet_060_00463920.pt --unaligned_loss vgg
If you find our code helpful in your research or work please cite our paper.
@inproceedings{wei2019single,
title={Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements},
author={Wei, Kaixuan and Yang, Jiaolong and Fu, Ying and David, Wipf and Huang, Hua},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
year={2019},
}
If you find any problem, please feel free to contact me (kxwei at princeton.edu kaixuan_wei at bit.edu.cn).
A brief self-introduction is required, if you would like to get an in-depth help from me.
Special thanks to @fqnchina and @ceciliavision for some discussions of this work.