Image matting with normalized weight and semi-supervised learning

TL;DR

This paper introduces a novel image matting method that uses a normalized weight parameter to balance sampling and propagation, combined with semi-supervised learning to refine trimaps automatically, enhancing performance especially with coarse trimaps.

Contribution

It proposes a new normalized weighting parameter for better control in sampling-propagation based matting and integrates semi-supervised learning to refine trimaps without user interaction.

Findings

Normalized weight parameter improves matting accuracy.

Semi-supervised learning refines trimaps automatically.

Significant performance gains on benchmark datasets.

Abstract

Image matting is an important vision problem. The main stream methods for it combine sampling-based methods and propagation-based methods. In this paper, we deal with the combination with a normalized weighting parameter, which could well control the relative relationship between information from sampling and from propagation. A reasonable value range for this parameter is given based on statistics from the standard benchmark dataset. The matting is further improved by introducing semi-supervised learning iterations, which automatically refine the trimap without user's interaction. This is especially beneficial when the trimap is coarse. The experimental results on standard benchmark dataset have shown that both the normalized weighting parameter and the semi-supervised learning iteration could significantly improve the matting performance.