Joint coarse-and-fine reasoning for deep optical flow
ICIP, Volume abs/1808.07416, 2017, Pages 2558-2562.
We propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine reasoning. The coarse reasoning is performed over a discrete classification space to obtain a general rough solution, while the fine details of the solution are o...More
Full Text (Upload PDF)
PPT (Upload PPT)