Removes reflections quickly and easily.

You can either:

• install it as a Python package,
• clone and use it as a repository, or
• use it as a web app on my website.

In your own project, just perform the following command:

# python refers to the virtual environment to install package to
python -m pip install fast-reflection-removal

Now, you can use the reflection removal in your project in the following manner:

from frr import FastReflectionRemoval

...
# numpy array with values between 0 and 1 of shape (H, W, C)
img = ...
# instantiate the algoroithm class
alg = FastReflectionRemoval(h = 0.11)
# run the algorithm and get result of shape (H, W, C)
dereflected_img = alg.remove_reflection(img)

...

1. Clone the project and go to its root directory.
2. Create and activate the virtual environment:

   # create the environment
   python3 -m venv "venv"
   # activate the environment
   source venv/bin/activate # on Windows ./venv/Scripts/activate.ps1 in Powershell

3. Install the necessary packages:

   python -m pip install --upgrade pip
   python -m pip install --upgrade wheel setuptools pip-tools

4. Install the packages from requirements and the project:

   make sync # on windows just perform the following commands: python -m piptools sync requirements.txt; python -m pip install -e .

Example:

# activate the environment
source venv/bin/activate # on Windows ./venv/Scripts/activate.ps1 in Powershell
frr "tests/test_frr/fixtures/toy_example.jpg" "out.jpg" -h 0.11

The program, in this example, loads input image from the path tests/test_frr/fixtures/toy_example.jpg, processes it with parameter h=0.11 and outputs it into out.jpg. More information about the parameters can be obtained by invoking frr --help.

Folders:

• docs: documentation.
• src: contains list of folders for sources, e.g. python.
• tests: tests that follow the structure of src/python.

This repository implements paper Fast Single Image Reflection Suppression via Convex Optimization authored by Yang Yang, Wenye Ma, Yin Zheng, Jian-Feng Cai and Weiyu Xu.