A multi-scale gradient based method for image completion

  • Authors:
  • Rui Lu;De Xu;Bing Li

  • Affiliations:
  • Institute of Computer Science and Engineering, Beijing Jiaotong University, Beijing, China;Institute of Computer Science and Engineering, Beijing Jiaotong University, Beijing, China;Institute of Computer Science and Engineering, Beijing Jiaotong University, Beijing, China

  • Venue:
  • SSIP'07 Proceedings of the 7th WSEAS International Conference on Signal, Speech and Image Processing
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Image completion is a challenging problem in computer graphics and computer vision. It refers to the problem of automatically filling holes in images left by the unwanted objects removal in a plausible way. Unlike previous methods we incorporate gradient components to get a global effect by performing local operations. At the same time in order to speed up convergence and further enforce global consistency, we use multiple-scale solution through a gauss pyramid. In the end Experiment results show promising performances compared with most of the existing algorithms.