TY - GEN
T1 - Learning to detect ground control points for improving the accuracy of stereo matching
AU - Spyropoulos, Aristotle
AU - Komodakis, Nikos
AU - Mordohai, Philippos
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/9/24
Y1 - 2014/9/24
N2 - While machine learning has been instrumental to the ongoing progress in most areas of computer vision, it has not been applied to the problem of stereo matching with similar frequency or success. We present a supervised learning approach for predicting the correctness of stereo matches based on a random forest and a set of features that capture various forms of information about each pixel. We show highly competitive results in predicting the correctness of matches and in confidence estimation, which allows us to rank pixels according to the reliability of their assigned disparities. Moreover, we show how these confidence values can be used to improve the accuracy of disparity maps by integrating them with an MRF-based stereo algorithm. This is an important distinction from current literature that has mainly focused on sparsification by removing potentially erroneous disparities to generate quasi-dense disparity maps.
AB - While machine learning has been instrumental to the ongoing progress in most areas of computer vision, it has not been applied to the problem of stereo matching with similar frequency or success. We present a supervised learning approach for predicting the correctness of stereo matches based on a random forest and a set of features that capture various forms of information about each pixel. We show highly competitive results in predicting the correctness of matches and in confidence estimation, which allows us to rank pixels according to the reliability of their assigned disparities. Moreover, we show how these confidence values can be used to improve the accuracy of disparity maps by integrating them with an MRF-based stereo algorithm. This is an important distinction from current literature that has mainly focused on sparsification by removing potentially erroneous disparities to generate quasi-dense disparity maps.
KW - 3D computer vision
KW - Stereo correspondence
UR - http://www.scopus.com/inward/record.url?scp=84911404074&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84911404074&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2014.210
DO - 10.1109/CVPR.2014.210
M3 - Conference contribution
AN - SCOPUS:84911404074
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1621
EP - 1628
BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
T2 - 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Y2 - 23 June 2014 through 28 June 2014
ER -