We describe a reconstruction method of multiple motion scenes, which are the scenes containing multiple moving objects, from uncalibrated views. Assuming that the objects are movi...
Abstract. In this work, we propose a model-based approach for estimating the 3D position and orientation of a dummy's head for crash test video analysis. Instead of relying on...
Juergen Gall, Bodo Rosenhahn, Stefan Gehrig, Hans-...
This paper describes a method for camera motion estimation based on real endoscope images and CT images for an endoscope navigation system. We have developed an endoscope navigati...
Jun Sugiyama, Hidenori Syouji, Kensaku Mori, Yasuh...
We present our system for the capturing and analysis of 3D facial motion. A high speed camera is used as capture unit in combination with two surface mirrors. The mirrors provide ...
Virtual view synthesis is essential for 3D teleconference systems like VIRTUE, which utilizes the motion parallax cue. In this paper we propose a multi-step view synthesis algorit...