Combinatorial Regularization of Descriptor Matching for Optical Flow Estimation
British Machine Vision Conference (BMVC), 2015
Abstract: One fundamental step in many state of the art optical flow methods is the initial
estimation of reliable correspondences. It is well-established to extract and match features
such as HOG to handle large displacements. We propose a combinatorial refinement of
the initial matching. Optimization is done in the space of affine motion, where we
regularize between neighboring points and similar regions. The evaluation on the MPI-Sintel
dataset shows that the proposed method removes outliers from the initial matching and
increases the number of reliable matches. The proposed refinement improves all optical
flow algorithms that build upon pre-computed correspondences.
Images and movies
BibTex reference
@InProceedings{DB15c, author = "B. Drayer and T. Brox", title = "Combinatorial Regularization of Descriptor Matching for Optical Flow Estimation", booktitle = "British Machine Vision Conference (BMVC)", year = "2015", url = "http://lmb.informatik.uni-freiburg.de/Publications/2015/DB15c" }