About this Project
This project aims to make a step forward in image matting, by developing novel algorithms and user interaction techniques that meet the requirements to quickly extract high quality objects from natural images. This research project is funded by Microsoft Research through its PhD Scholarship Programme.
In our "High-resolution matting framework (CVPR 2008)", we developed a new interactive approach for single image matting which splits the task of extracting a foreground object from a single background into two steps: Interactive trimap extraction and trimap-based alpha matting. By doing this we gain considerably in terms of speed and quality and in contrast to previous work are able to deal with high resolution images.
A number of matting algorithms rely on modeling the color of the user marked foreground and background regions to infer the optimal alpha value for every pixel. In our "Improved color model matting" paper (BMVC 2008), we exploit information from global color models to find better local estimates for the true fore- and background colors to finally estimate better alpha mattes.
Funding provided by
- C. Rhemann, C. Rother, M. Gelautz, Improving Color Modeling for Alpha Matting, BMVC 2008, Leeds, UK (2008) PDF
- C. Rhemann, C. Rother, A. Rav-Acha, T. Sharp, High Resolution Matting via Interactive Trimap Segmentation, CVPR 2008, Alaska (2008) PDF; Supplementary Material: PDF; Technical Report: PDF
- C. Rhemann, A Graph-based Approach to Optical Flow Estimation, Junior Scientist Conference 2006, Vienna, Austria, pp. 61-63, 2006 PDF
- Michael Bleyer, Margrit Gelautz, Christoph Rhemann, Segmentation-based Motion with Occlusions Using Graph-Cut Optimization, DAGM 2006, Lecture Notes in Computer Science (LNCS) 4174, pp. 465–474, 2006 PDF
- Michael Bleyer, Margrit Gelautz, Christoph Rhemann, Colour Segmentation-based Computation of Dense Optical Flow with Application to Video Object Segmentation, OEGAI-Journal, 24(1), pp 11-15, 2005 PDF
- Michael Bleyer, Margrit Gelautz, Christoph Rhemann, Region-based Optical Flow Estimation with Treatment of Occlusions, Joint Hungarian-Austrian Conference on Image Processing and Pattern Recognition, pp. 235-242, 2005 PDF