In this paper we considerably improve on a state-of-the-art alpha matting approach by incorporating a new prior which is based on the image formation process. In particular, we model the prior probability of an alpha matte as the convolution of a high-resolution binary segmentation with the spatially varying point spread function (PSF) of the camera. Our main contribution is a new and efficient de-convolution approach that recovers the prior model, given an approximate alpha matte. By assuming that the PSF is a kernel with a single peak, we are able to recover the binary segmentation with an MRF-based approach, which exploits flux and a new way of enforcing connectivity. The spatially varying PSF is obtained via a partitioning of the image into regions of similar defocus. Incorporating our new prior model into a state-of-the-art matting technique produces results that outperform all competitors, which we confirm using a publicly available benchmark.
C. Rhemann, C. Rother, P. Kohli, M. Gelautz: "A Spatially Varying PSF-based Prior for Alpha Matting"; Poster: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010. CVPR '10, San Francisco, USA; 06-13-2010 - 06-18-2010; in: "IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2010", IEEE, (2010), ISBN: 978-1-4244-6984-0; 8 pages.
Click into the text area and press Ctrl+A/Ctrl+C or ⌘+A/⌘+C to copy the BibTeX into your clipboard… or download the BibTeX.