Secrets in Computing Optical Flow by Convolutional Networks

10/04/2017

∙

by   Junxuan Li, et al.

∙

0

∙

share

Convolutional neural networks (CNNs) have been widely used over many areas in compute vision. Especially in classification. Recently, FlowNet and several works on opti- cal estimation using CNNs shows the potential ability of CNNs in doing per-pixel regression. We proposed several CNNs network architectures that can estimate optical flow, and fully unveiled the intrinsic different between these structures.