Learning for Optical Flow Using Stochastic Optimization
ECCV (2), pp. 379-391, 2008.
flow fieldoptical flowtraining setmissing data valuestochastic optimizationMore(10+)
We present a technique for learning the parameters of a continuous-state Markov random field (MRF) model of optical flow, by minimizing the training loss for a set of ground-truth images using simultaneous perturbation stochastic approximation (SPSA). The use of SPSA to directly minimize the training loss offers several advantages over mo...More
Full Text (Upload PDF)
PPT (Upload PPT)