TY - GEN
T1 - The self-aware matching measure for stereo
AU - Mordohai, Philippos
PY - 2009
Y1 - 2009
N2 - We revisit stereo matching functions, a topic that is considered well understood, from a different angle. Our goal is to discover a transformation that operates on the cost or similarity measures between pixels in binocular stereo. This transformation should produce a new matching curve that results in higher matching accuracy. The desired transformation must have no additional parameters over those of the original matching function and must result in a new matching function that can be used by existing local, global and semi-local stereo algorithms without having to modify the algorithms. We propose a transformation that meets these requirements, taking advantage of information derived from matching the input images against themselves. We analyze the behavior of this transformation, which we call Self-Aware Matching Measure (SAMM), on a diverse set of experiments on data with ground truth. Our results show that the SAMM improves the performance of dense and semi-dense stereo. Moreover, as opposed to the current state of the art, it does not require distinctiveness to match pixels reliably.
AB - We revisit stereo matching functions, a topic that is considered well understood, from a different angle. Our goal is to discover a transformation that operates on the cost or similarity measures between pixels in binocular stereo. This transformation should produce a new matching curve that results in higher matching accuracy. The desired transformation must have no additional parameters over those of the original matching function and must result in a new matching function that can be used by existing local, global and semi-local stereo algorithms without having to modify the algorithms. We propose a transformation that meets these requirements, taking advantage of information derived from matching the input images against themselves. We analyze the behavior of this transformation, which we call Self-Aware Matching Measure (SAMM), on a diverse set of experiments on data with ground truth. Our results show that the SAMM improves the performance of dense and semi-dense stereo. Moreover, as opposed to the current state of the art, it does not require distinctiveness to match pixels reliably.
UR - http://www.scopus.com/inward/record.url?scp=77953227246&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77953227246&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2009.5459409
DO - 10.1109/ICCV.2009.5459409
M3 - Conference contribution
AN - SCOPUS:77953227246
SN - 9781424444205
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 1841
EP - 1848
BT - 2009 IEEE 12th International Conference on Computer Vision, ICCV 2009
T2 - 12th International Conference on Computer Vision, ICCV 2009
Y2 - 29 September 2009 through 2 October 2009
ER -