- The implementation of "Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance".
- The code has been test on a PC with following environment
- Ubuntu 18.04
- Python 3.7.5
- PyTorch 1.2.0
- cudatoolkit 10.0
- NVIDIA RTX 2080Ti
- Synthetic: 7643 images from Pascal VOC dataset, image choices and the data synthesis protocol are same as ERRNet.
- Real: 90 real-world images from Berkeley real dataset.
Real20: 20 real testing images from Berkeley real dataset.
Real45: 45 real testing images from CEILNet dataset.
SIR dataset: three sub-datasets (Solid, Postcard, Wild) from SIR dataset.
We provide Real20 and Real45 in
./testsetsfolder, the SIR dataset is not provided due to their policy, download here and put it under
./testsetsfolder. Please organize the SIR dataset according to our code implementation.
- Download our pre-trained model and put the
Test with the pre-trained model
$ cd RAGNet $ python test.py
- Download the vgg19-pretrained model and put it into
- Organize the training dataset according to our code implementation, i.e.,
$ cd synthetic $ mkdir transmission_layer $ mkdir blended
$ cd RAGNet $ python train.py