Sparse Coding for Alpha Matting

TL;DR

This paper introduces a sparse coding approach to alpha matting that leverages unpaired foreground and background samples, improving estimation accuracy and extending effectively to videos with temporal coherence.

Contribution

It reinterprets alpha matting as sparse coding, allowing the use of unpaired samples and providing a unified framework for both image and video matting.

Findings

Outperforms state-of-the-art in image matting

Effective in maintaining temporal coherence in videos

Provides both qualitative and quantitative improvements

Abstract

Existing color sampling based alpha matting methods use the compositing equation to estimate alpha at a pixel from pairs of foreground (F) and background (B) samples. The quality of the matte depends on the selected (F,B) pairs. In this paper, the matting problem is reinterpreted as a sparse coding of pixel features, wherein the sum of the codes gives the estimate of the alpha matte from a set of unpaired F and B samples. A non-parametric probabilistic segmentation provides a certainty measure on the pixel belonging to foreground or background, based on which a dictionary is formed for use in sparse coding. By removing the restriction to conform to (F,B) pairs, this method allows for better alpha estimation from multiple F and B samples. The same framework is extended to videos, where the requirement of temporal coherence is handled effectively. Here, the dictionary is formed by samples from multiple frames. A multi-frame graph model, as opposed to a single image as for image matting, is proposed that can be solved efficiently in closed form. Quantitative and qualitative evaluations on a benchmark dataset are provided to show that the proposed method outperforms current state-of-the-art in image and video matting.