Image matting with normalized weight and semi-supervised learning
This work addresses image matting for computer vision applications, offering incremental improvements through parameter normalization and automated trimap refinement.
The paper tackled the problem of image matting by introducing a normalized weighting parameter to control the balance between sampling and propagation methods, and used semi-supervised learning to refine trimaps automatically, resulting in significant performance improvements on a standard benchmark dataset.
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.