Research Article

As-consistent-As-possible compositing of virtual objects and video sequences

  1. Guofeng Zhang,
  2. Xueying Qin*,
  3. Xiaobo An,
  4. Wei Chen,
  5. Hujun Bao

Article first published online: 14 JUN 2006

DOI: 10.1002/cav.134

Issue

Computer Animation and Virtual Worlds

Computer Animation and Virtual Worlds

Special Issue: CASA 2006

Volume 17, Issue 3-4, pages 305–314, July 2006

Additional Information

How to Cite

Zhang, G., Qin, X., An, X., Chen, W. and Bao, H. (2006), As-consistent-As-possible compositing of virtual objects and video sequences. Comp. Anim. Virtual Worlds, 17: 305–314. doi: 10.1002/cav.134

Author Information

*State Key Lab of CAD&CG, Zhejiang University, P.R. China.

Publication History

  1. Issue published online: 14 JUN 2006
  2. Article first published online: 14 JUN 2006
  3. Manuscript Accepted: 10 MAY 2006
  4. Manuscript Revised: 2 MAY 2006
  5. Manuscript Received: 10 APR 2006

Funded by

  • 973 program of China. Grant Number: 2002CB312104
  • NSF of China. Grant Numbers: 60021201, 60373035
  • Specialized Research Fund for the Doctoral Program of Higher Education. Grant Number: 20030335083

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

Get PDF (538K)

Keywords:

  • structure and motion recovery;
  • 3D reconstruction;
  • multi-baseline stereo;
  • Augmented Video;
  • interaction

Abstract

We present an efficient approach that merges the virtual objects into video sequences taken by a freely moving camera in a realistic manner. The composition is visually and geometrically consistent through three main steps. First, a robust camera tracking algorithm based on key frames is proposed, which precisely recovers the focal length with a novel multi-frame strategy. Next, the concerned 3D models of the real scenes are reconstructed by means of an extended multi-baseline algorithm. Finally, the virtual objects in the form of 3D models are integrated into the real scenes, with special cares on the interaction consistency including shadow casting, occlusions, and object animation. A variety of experiments have been implemented, which demonstrate the robustness and efficiency of our approach. Copyright © 2006 John Wiley & Sons, Ltd.

Get PDF (538K)