Multi-view Coding with Dense Correspondence Fields Benjamin Meyer, Christian Lipski, Björn Scholz, Marcus Magnor

Benjamin Meyer, Christian Lipski, Björn Scholz, and Marcus Magnor: "Multi-view Coding with Dense Correspondence Fields", in Proc. IEEE International Symposium on Consumer Electronics (ISCE), pp. 117–120, June 2010. Part of project "Virtual Video Camera". [pdf] [bib] [windows demo]

Abstract

We present a fast decoder for free-viewpoint video navigation. Our free-viewpoint video data consist of simultaneously recorded video streams captured with multiple cameras plus additional dense correspondence information. Neither the size nor the representation of the data is appropriate for real-time rendering. We propose a data compression approach for multi-view video sequences that allows for a real-time decoding and playback of long sequences from hard drive.

TU Braunschweig - Fakultät für Mathematik und Informatik - Computer Graphics - Publications - Multi-view Coding with Dense Correspondence Fields