Reflection-Removal

This code is based on tensorflow. The github link for the code is https://github.com/ChiranjivMalhi/perceptual-reflection-removal.

Setup

Download VGG-19. Search imagenet-vgg-verydeep-19 in this page and download imagenet-vgg-verydeep-19.mat. We need the pre-trained VGG-19 model for our hypercolumn input and feature loss
Download pre-trained model here.
Move both the files into your Drive and name the folder reflection-dataset.
Go to Colab link https://colab.research.google.com/drive/1uCr9e3Dd8n3xzBVM7Oq1Y9RFFvlzRscB?usp=sharing
Run all the commands.

If you want to test on the provided test images (e.g. in ./test_images/real/), keep it as it is.
If you want to test on your images upload the images in (e.g. in ./test_images/real/) folder.
Then run the last command on Colab again.
Test results can be found in ./test_results/

Name		Name	Last commit message	Last commit date
Latest commit History 35 Commits
teaser		teaser
test_images		test_images
LICENSE		LICENSE
README.md		README.md
discriminator.py		discriminator.py
env.yml		env.yml
main.py		main.py