Title
Aggregation of local parametric candidates with exemplar-based occlusion handling for optical flow.
Abstract
•An occlusion-aware optical flow estimation based on a discrete aggregation framework.•Accurate parametric patch-based scheme for motion candidate computation with an efficient integration of feature matching.•A generic exemplar-based approach for recovering motion in occluded regions.•Joint motion field and occlusion map estimation guided by an occlusion confidence map obtained from motion candidates.•State-of-the-art results on the challenging MPI Sintel dataset for large displacements and occlusions.
Year
DOI
Venue
2016
10.1016/j.cviu.2015.11.020
Computer Vision and Image Understanding
Keywords
DocType
Volume
Optical flow,Occlusion,Large displacement,Local parametric motion,Aggregation framework
Journal
145
Issue
ISSN
Citations 
C
1077-3142
12
PageRank 
References 
Authors
0.79
76
3
Name
Order
Citations
PageRank
Denis Fortun1425.26
Patrick Bouthemy22675286.70
Charles Kervrann393467.36