"Mind the gap": tele-registration for structure-driven image completion

  • Authors:
  • Hui Huang;Kangxue Yin;Minglun Gong;Dani Lischinski;Daniel Cohen-Or;Uri Ascher;Baoquan Chen

  • Affiliations:
  • Shenzhen VisuCA Key Lab / SIAT;Shenzhen VisuCA Key Lab / SIAT;Memorial University of Newfoundland;The Hebrew University of Jerusalem;Tel-Aviv University;The University of British Columbia;Shenzhen VisuCA Key Lab / SIAT and Shandong University

  • Venue:
  • ACM Transactions on Graphics (TOG)
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

Concocting a plausible composition from several non-overlapping image pieces, whose relative positions are not fixed in advance and without having the benefit of priors, can be a daunting task. Here we propose such a method, starting with a set of sloppily pasted image pieces with gaps between them. We first extract salient curves that approach the gaps from non-tangential directions, and use likely correspondences between pairs of such curves to guide a novel tele-registration method that simultaneously aligns all the pieces together. A structure-driven image completion technique is then proposed to fill the gaps, allowing the subsequent employment of standard in-painting tools to finish the job.