Devon: Deformable Volume Network for Learning Optical Flow.

RSS Source
Authors
Yao Lu, Jack Valmadre, Heng Wang, Juho Kannala, Mehrtash Harandi, Philip H. S. Torr

We propose a lightweight neural network model, Deformable Volume Network(Devon) for learning optical flow. Devon benefits from a multi-stage frameworkto iteratively refine its prediction. Each stage is by itself a neural networkwith an identical architecture. The optical flow between two stages ispropagated with a newly proposed module, the deformable cost volume. Thedeformable cost volume does not distort the original images or their featuremaps and therefore avoids the artifacts associated with warping, a commondrawback in previous models. Devon only has one million parameters. Experimentsshow that Devon achieves comparable results to previous neural network models,despite of its small size.

Stay in the loop.

Subscribe to our newsletter for a weekly update on the latest podcast, news, events, and jobs postings.