Adaptive support-weight approach for correspondence search

Korea Advanced Institute of Science and Technology

PubMed
Indexed incrossrefpubmed

Abstract

We present a new window-based method for correspondence search using varying support-weights. We adjust the support-weights of the pixels in a given support window based on color similarity and geometric proximity to reduce the image ambiguity. Our method outperforms other local methods on standard stereo benchmarks.

Citation impact

1,189
total citations
FWCI
32.24
Percentile
100%
References
29
Citations per year

Authors

2

Topics & keywords

Keywords
  • Artificial intelligence
  • Pixel
  • Computer science
  • Ambiguity
  • Window (computing)
  • Similarity (geometry)
  • Pattern recognition (psychology)
  • Computer vision
No related works found for this paper.