An Alternative Matting Laplacian

TL;DR

This paper introduces an alternative formulation of the matting Laplacian that provides greater control over priors and improves efficiency in upscaling transparency maps, enhancing object cutout and transparency estimation.

Contribution

It proposes a new matting Laplacian formulation that offers more flexible prior controls and better upscaling efficiency compared to existing methods.

Findings

More flexible control over matting priors.

Efficient upscaling of transparency maps.

Improved object cutout quality.

Abstract

Cutting out and object and estimate its transparency mask is a key task in many applications. We take on the work on closed-form matting by Levin et al., that is used at the core of many matting techniques, and propose an alternative formulation that offers more flexible controls over the matting priors. We also show that this new approach is efficient at upscaling transparency maps from coarse estimates.