A Variable Window Approach to Early Vision

  • Authors:
  • Yuri Boykov;Olga Veksler;Ramin Zabith

  • Affiliations:
  • Cornell Univ., Ithaca, NY;Cornell Univ., Ithaca, NY;Cornell Univ., Ithaca, NY

  • Venue:
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Year:
  • 1998

Quantified Score

Hi-index 0.14

Visualization

Abstract

Early vision relies heavily on rectangular windows for tasks such as smoothing and computing correspondence. While rectangular windows are efficient, they yield poor results near object boundaries. We describe an efficient method for choosing an arbitrarily shaped connected window, in a manner that varies at each pixel. Our approach can be applied to several problems, including image restoration and visual correspondence. It runs in linear time, and takes a few seconds on traditional benchmark images. Performance on both synthetic and real imagery appears promising.