Layer-Constraint-Based visibility for volumetric multi-view reconstruction

  • Authors:
  • Yumo Yang;Liuxin Zhang;Yunde Jia

  • Affiliations:
  • Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing, P.R. China;Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing, P.R. China;Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing, P.R. China

  • Venue:
  • MMM'10 Proceedings of the 16th international conference on Advances in Multimedia Modeling
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Visibility estimation is one of the most difficult problems in multi-view reconstruction using volumetric approaches. In this paper, we present a novel approach called layer-constraint-based visibility (LCBV) to estimating visibility. Based on the layered state of a scene and photo-consistency constraint, this method can determine the more accurate visibility for every point in a scene. We use LCBV in multi-view reconstruction using volumetric graph cuts and obtain satisfactory results on both synthetic and real datasets. We also discuss quantitative error analysis to judge visibility techniques.