filename     : Tan19a.pdf
entry        : inproceedings
conference   : Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, June 16-20, 2019
pages        : 3055-3063
year         : 2019
month        : June
title        : Learning-based Sampling for Natural Image Matting
subtitle     :
author       : Jingwei Tang and Yağız Aksoy Cengiz Öztireli and Markus Gross and Tunç Ozan Aydın
booktitle    : Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
ISSN/ISBN    : 978-1-7281-3293-8
editor       : 
publisher    :
publ.place   :
volume       :
issue        :
language     : english
keywords     : 
abstract     : The goal of natural image matting is the estimation of opacities of a user-defined foreground object that is essential in creating realistic composite imagery. Natural matting is a challenging process due to the high number of unknowns in the mathematical modeling of the problem, namely the opacities as well as the foreground and background layer colors, while the original image serves as the single observation. In this paper, we propose the estimation of the layer colors through the use of deep neural networks prior to the opacity estimation. The layer color estimation is a better match for the capabilities of neural networks, and the availability of these colors substantially increase the performance of opacity estimation due to the reduced number of unknowns in the compositing equation. A prominent approach to matting in parallel to ours is called sampling-based matting, which involves gathering color samples from known-opacity regions to predict the layer colors. Our approach outperforms not only the previous hand-crafted sampling algorithms, but also current data-driven methods. We hence classify our method as a hybrid sampling- and learning-based approach to matting, and demonstrate the effectiveness of our approach through detailed ablation studies using alternative network architectures.