Interactive Shape from Shading

  • Authors:
  • Gang Zeng;Yasuyuki Matsushita;Long Quan;Heung-Yeung Shum

  • Affiliations:
  • Hong Kong University of Science and Technology;Microsoft Research Asia;Hong Kong University of Science and Technology;Microsoft Research Asia

  • Venue:
  • CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Shape from shading (SfS) has always been difficult for real applications due to its intrinsic ill-posedness. In this paper, we propose an interactive SfS method whichefficiently uses human knowledge in order to resolve ambiguity. We propose a global solution of continuous surfaces with a few constraints of surface normals that are interactively imposed to regularize the problem. A surface is divided into local patches, and each local solution is estimated with a fast marching SfS. It is shown that the boundaries of local solutions constitute a weighted Voronoi diagram, which allows for the formation of a global solution from the local ones. Finally, we optimize this global estimation by minimizing an energy functional based on shading and smoothness priors. Reconstruction results from both synthetic and real images demonstrate the usability of the new approach for various modeling applications.