Research

Teaching

Forums

Staff

Contact

Intranet

Research Projects
Past and current research projects in the areas of virtual reality, media processing and web-based information systems.

Student and Thesis Projects, Jobs
Available student and thesis projects and job offers.

Scientific Publications
Details and downloads publications, technical reports and thesis papers.

C. Rhemann, C. Rother, A. Rav-Acha, T. Sharp, High Resolution Matting via Interactive Trimap Segmentation, CVPR 2008, Alaska

by Christoph Rhemann, Carsten Rother, Alex Rav-Acha, Toby Sharp

Abstract

We present a new approach to the matting problem which splits the task into two steps: interactive trimap extraction followed by trimap-based alpha matting. By doing so we gain considerably in terms of speed and quality and are able to deal with high resolution images. This paper has three contributions: (i) a new trimap segmentation method using parametric max-flow; (ii) an alpha matting technique for high resolution images with a new gradient preserving prior on alpha; (iii) a database of 27 ground truth alpha mattes of still objects, which is considerably larger than previous databases and also of higher quality. The data-base is used to train our system and to validate that both our trimap extraction and our matting method improve on state-of-the-art techniques.

Download

Follow the link below to download the document. To view PDF documents, you need Acrobat Reader. For PostScript files, use either Acrobat Distiller (commercial) or GhostScript (free).

Download: RhemannRotherRavAchaSharpCVPR08.pdf
Version: 1.0

Details

C. Rhemann, C. Rother, A. Rav-Acha, T. Sharp, High Resolution Matting via Interactive Trimap Segmentation, CVPR 2008, Alaska
TR Number:	TR-188-2-2008-18
First Published:	2008
Publishing History:	CVPR 2008, Alaska, June 2008
Keywords:	Image Segmentation, Image Matting

Print this Page
Display a printer-friendly version of this page.