Skip to content
Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements (CVPR 2019)
Python
Branch: master
Clone or download
Latest commit 5c1a7f9 Aug 4, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data init Mar 30, 2019
imgs add example Mar 31, 2019
models init Mar 30, 2019
options
util init Mar 30, 2019
.gitignore add example Mar 31, 2019
README.md Update README.md Aug 4, 2019
VOC2012_224_train_png.txt init Mar 30, 2019
engine.py init Mar 30, 2019
real_test.txt init Mar 30, 2019
test_errnet.py update readme May 26, 2019
train_errnet.py update readme May 26, 2019

README.md

ERRNet

The implementation of CVPR 2019 paper "Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements"

News (30/06/2019): Our suppl. material, poster, pretrained model and collected unaligned dataset are now available at Google Drive.

Highlights

  • Our network can extract the background image layer devoid of reflection artifacts, as in the example:

  • We captured a new dataset containing 450 unaligned image pairs that are considerably easier to collect. Image samples from our unaligned dataset are shown below:

  • We introduce a simple but powerful alignment-invariant loss function to facilitate exploiting misaligned real-world training data. Finetuning on unaligned image pairs with our loss leads to sharp and reflection-free results, in contrast to the blurry ones when using a conventional pixel-wise loss (L1, L2, e.t.c.). The resulting images finetuned by different losses are shown below: (Left: Pixel-wise loss; Right: Ours)

Prerequisites

  • Python >=3.5, PyTorch >= 0.4.1
  • Requirements: opencv-python, tensorboardX, visdom
  • Platforms: Ubuntu 16.04, cuda-8.0

Quick Start

1. Preparing your training/testing datasets

Training dataset

  • 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

Testing 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.)

2. Playing with aligned data

Testing

  • Download our pretrained model from Google Drive and move errnet_060_00463920.pt to checkpoints/errnet/.
  • Evaluate the model performance by python test_errnet.py --name errnet -r --icnn_path checkpoints/errnet/errnet_060_00463920.pt --hyper

Training

  • Reproduce our results by python train_errnet.py --name errnet --hyper
  • Check options/errnet/train_options.py to see more training options.

3. (TODO) Playing with unaligned data

Citation

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},
 }

Contact

If you find any problem, please feel free to contact me (kaixuan_wei at bit.edu.cn). A brief self-introduction is required, if you would like to get an in-depth help from me.

Acknowledgments

You can’t perform that action at this time.