Polar Matte: Fully Computational Ground-Truth-Quality Alpha Matte Extraction for Images and Video using Polarized Screen Matting

Kenji Enomoto, T. J. Rhodes, Brian L. Price, Gavin Miller

Abstract: The creation of high-quality alpha mattes as ground-truth data for video matting is typically a laborious task. The trade-off between accuracy, manual corrections, and capture constraints often produces erroneous results or is cost prohibitive. We propose Po larMatte, a fully computational alpha matte extraction method for images and video without compromise between quality and practicality. A single polarization camera is used to capture dynamic scenes backlit by an off-the-shelf LCD monitor. PolarMatte exploits the polarization channel to compute the per-pixel opacity of the target scene, including the transparency of fine-details, translucent objects, and optical/motion blur. We leverage polarization clues to robustly detect indistin-guishable pixels, and extract the alpha matte value at po-larized foreground reflections with a polarimetric matting Laplacian. Quantitative and qualitative evaluation demon-strate our ability to computationally extract ground-truth-quality alpha mattes without human labour.

External IDs:dblp:conf/cvpr/EnomotoRPM24