Recent methods for reconstructing surfaces from multiple images

  • Authors:
  • Gang Zeng;Maxime Lhuillier;Long Quan

  • Affiliations:
  • Dep. of Computer Science, HKUST, Kowloon, Hong Kong;LASMEA, UMR CNRS 6602, Université Blaise-Pascal, Aubière, France;Dep. of Computer Science, HKUST, Kowloon, Hong Kong

  • Venue:
  • IWMM'04/GIAE'04 Proceedings of the 6th international conference on Computer Algebra and Geometric Algebra with Applications
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

Many objects can be mathematically represented as smooth surfaces with arbitrary topology, and smooth surface reconstruction from images could be cast into a variational problem. The main difficulties are the intrinsic ill-posedness of the reconstruction, image noise, efficiency and scalability. In this paper, we discuss the reconstruction approaches that use volumetric, graph-cut, and level-set optimization tools; and the objective functionals that use different image information, silhouette, photometry, and texture. Our discussion is accompanied by the implementations of these approaches on real examples.