Header logo is ps

Optical Flow Estimation using a Spatial Pyramid Network

2017

Conference Paper

ps


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. Unlike the recent FlowNet approach, the networks do not need to deal with large motions; these are dealt with by the pyramid. This has several advantages. First, our Spatial Pyramid Network (SPyNet) is much simpler and 96% smaller than FlowNet in terms of model parameters. This makes it more efficient and appropriate for embedded applications. Second, since the flow at each pyramid level is small (< 1 pixel), a convolutional approach applied to pairs of warped images is appropriate. Third, unlike FlowNet, the learned convolution filters appear similar to classical spatio-temporal filters, giving insight into the method and how to improve it. Our results are more accurate than FlowNet on most standard benchmarks, suggesting a new direction of combining classical flow methods with deep learning.

Author(s): Anurag Ranjan and Michael Black
Book Title: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Year: 2017
Month: July

Department(s): Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Event Name: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2017
Event Place: Honolulu, HI, USA

Links: pdf
SupMat
project/code

BibTex

@inproceedings{spynet,
  title = {Optical Flow Estimation using a Spatial Pyramid Network},
  author = {Ranjan, Anurag and Black, Michael},
  booktitle = {IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  month = jul,
  year = {2017},
  month_numeric = {7}
}