Computing the Stereo Matching Cost With a Convolutional Neural Network

Jure Zbontar; Yann LeCun

CVPR 2015poster1004 citations

Computing the Stereo Matching Cost With a Convolutional Neural Network

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.

BibTeX

@inproceedings{cvpr2015_computingthester,
  title = {Computing the Stereo Matching Cost With a Convolutional Neural Network},
  author = {Jure Zbontar and Yann LeCun},
  booktitle = {CVPR 2015},
  year = {2015}
}