Awesome
Approximate Fast Foreground Colour Estimation
Official repository for the paper Approximate Fast Foreground Colour Estimation. ICIP 2021. Awarded Best Industry paper.
<img src="./images/radius_slide_portrait.gif" style="float: center;" width="450" height="600">Naively compositing without an estimate of foreground colour leads to bleed-through of the original background.
In this work, we propose a foreground estimation technique. Our method can be implemented 11 lines of Python code and yields comparable results to the full approach [1], while also being faster.
API Usage
PhotoRoom includes foreground estimation by default in the Backround Removal API, see documentation.
Requirements
- numpy # For mathematical operations.
- opencv-python # Efficient blur implementation.
Citation
@INPROCEEDINGS{ApproxForegroundForte2021,
author={Marco Forte},
booktitle={2021 IEEE International Conference on Image Processing (ICIP)},
title={Approximate Fast Foreground Colour Estimation},
year={2021},
doi={10.1109/ICIP42928.2021.9506164}}