Stereo matching as a nearest-neighbor problem

Journal Article (Journal Article)

We propose a representation of images, called intrinsic curves, that transforms stereo matching from a search problem into a nearest-neighbor problem. Intrinsic curves are the paths that a set of local image descriptors trace as an image scanline is traversed from left to right. Intrinsic curves are ideally invariant with respect to disparity. Stereo correspondence then becomes a trivial lookup problem in the ideal case. We also show how to use intrinsic curves to match real images in the presence of noise, brightness bias, contrast fluctuations, moderate geometric distortion, image ambiguity, and occlusions. In this case, matching becomes a nearest-neighbor problem, even for very large disparity values. ©1998 IEEE.

Full Text

Duke Authors

Cited Authors

  • Tomasi, C; Manduchi, R

Published Date

  • December 1, 1998

Published In

Volume / Issue

  • 20 / 3

Start / End Page

  • 333 - 340

International Standard Serial Number (ISSN)

  • 0162-8828

Digital Object Identifier (DOI)

  • 10.1109/34.667890

Citation Source

  • Scopus