Polarized Color Screen Matting
Kenji Enomoto, Scott Cohen, Brian Price, TJ Rhodes
Abstract
This paper considers the long-standing problem of extracting alpha mattes from video using a known background. While various color-based or polarization-based approaches have been studied in past decades, the problem remains ill-posed because the solutions solely rely on either color or polarization. We introduce Polarized Color Screen Matting, a single-shot, per-pixel matting theory for alpha matte and foreground color recovery using both color and polarization cues. Through a theoretical analysis of our diffuse-specular polarimetric compositing equation, we derive practical closed-form matting methods with their solvability conditions. Our theory concludes that an alpha matte can be extracted without manual corrections using off-the-shelf equipment such as an LCD monitor, polarization camera, and unpolarized lights with calibrated color. Experiments on synthetic and real-world datasets verify the validity of our theory and show the capability of our matting methods on real videos with quantitative and qualitative comparisons to color-based and polarization-based matting methods.
BibTeX
@InProceedings{Enomoto_2025_CVPR,
author = {Enomoto, Kenji and Cohen, Scott and Price, Brian and Rhodes, TJ},
title = {Polarized Color Screen Matting},
booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)},
month = {June},
year = {2025},
pages = {391-399}
}