Header logo is ps

SPyNet: Optical Flow Estimation using a Spatial Pyramid Network

2017-04-01


We learn to compute optical flow by combining a classical spatial-pyramid formulation with deep learning. This estimates large motions in a coarse-to-fine approach by warping one image of a pair at each pyramid level by the current flow estimate and computing an update to the flow. Instead of the standard minimization of an objective function at each pyramid level, we train one deep network per level to compute the flow update. Check the website for updates; we provide code for the original SypNet as well as an end-to-end trainable version.

Author(s): Anurag Ranjan, Michael Black
Department(s): Perceiving Systems
Publication(s): Optical Flow Estimation using a Spatial Pyramid Network
Authors: Anurag Ranjan, Michael Black
Release Date: 2017-04-01
Copyright: Max Planck Gesellschaft
Repository: https://github.com/anuragranj/spynet
External Link: http://spynet.is.tue.mpg.de/