L1-regularized Reconstruction Error as Alpha Matte
This addresses video matting for computer vision applications, but it is incremental as it builds on existing sampling-based methods with a new error measure.
The paper tackles the problem of video alpha matting by proposing an algorithm that uses L1-regularized reconstruction error as a measure for the alpha matte, achieving effectiveness demonstrated through qualitative and quantitative evaluations on a dedicated video matting dataset.
Sampling-based alpha matting methods have traditionally followed the compositing equation to estimate the alpha value at a pixel from a pair of foreground (F) and background (B) samples. The (F,B) pair that produces the least reconstruction error is selected, followed by alpha estimation. The significance of that residual error has been left unexamined. In this letter, we propose a video matting algorithm that uses L1-regularized reconstruction error of F and B samples as a measure of the alpha matte. A multi-frame non-local means framework using coherency sensitive hashing is utilized to ensure temporal coherency in the video mattes. Qualitative and quantitative evaluations on a dataset exclusively for video matting demonstrate the effectiveness of the proposed matting algorithm.