Learning a Confidence Measure for Optical Flow


We present a supervised learning based method to estimate a per-pixel confidence for optical flow vectors. Regions of low texture and pixels close to occlusion boundaries are known to be difficult for optical flow algorithms. Using a spatiotemporal feature vector, we estimate if a flow algorithm is likely to fail in a given region. Our method is not restricted to any specific class of flow algorithm, and does not make any scene specific assumptions. By automatically learning this confidence we can combine the output of several computed flow fields from different algorithms to select the best performing algorithm per pixel.

Our optical flow confidence measure allows one to achieve better overall results by discarding the most troublesome pixels. We illustrate the effectiveness of our method on four different optical flow algorithms over a variety of real and synthetic sequences. For algorithm selection, we achieve the top overall results on a large test set, and at times even surpasses the results of the best algorithm among the candidates.


PAMI 2012
Learning a Confidence Measure for Optical Flow
Oisin Mac Aodha, Ahmad Humayun, Marc Pollefeys and Gabriel J. Brostow
PAMI 2013
[paper] [supp material 1] [supp material 2] [bibtex]



UCL Ground Truth Optical Flow Dataset v1.2


Version 1.0 can be downloaded here [code] , with instructions available here [instructions].

Updated v1.2
Maya python code for generating ground truth optical flow.
[Maya GetFlow Code]

Contact: o dot macaodha at cs.ucl.ac.uk