The Maximal Self-dissimilarity Interest Point Detector

  title={The Maximal Self-dissimilarity Interest Point Detector},
  author={Federico Tombari and Luigi di Stefano},
  journal={IPSJ Trans. Computer Vision and Applications},
We propose a novel interest point detector stemming from the intuition that image patches which are highly dissimilar over a relatively large extent of their surroundings hold the property of being repeatable and distinctive. This concept of contextual self-dissimilarity reverses the key paradigm of recent successful techniques such as the Local Self… CONTINUE READING