conference paper Open access
Computing the stereo matching cost with a convolutional neural network
Jure Žbontara b, Yann LeCunc d
- aUniversity of Ljubljana
- bUniversity of Ljubljana, Kongresni trg 12, 1000, Slovenia
- cNew York University
- dNew York University, United States
IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/ProceedingsInstitute of Electrical and Electronics Engineers2015-06-01 819 citations25 references
Looking for the full paper…
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
We present a method for extracting depth information from a rectified image pair. We train a convolutional neural network to predict how well two image patches match and use it to compute the stereo matching cost. The cost is refined by cross-based cost aggregation and semiglobal matching, followed by a left-right consistency check to eliminate errors in the occluded regions. Our stereo method achieves an error rate of 2.61% on the KITTI stereo dataset and is currently (August 2014) the top performing method on this dataset.