FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Citations Over TimeTop 1% of 2017 papers

Abstract

The FlowNet demonstrated that optical flow estimation can be cast as a learning problem. However, the state of the art with regard to the quality of the flow has still been defined by traditional methods. Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods. In this paper, we advance the concept of end-to-end learning of optical flow and make it work really well. The large improvements in quality and speed are caused by three major contributions: first, we focus on the training data and show that the schedule of presenting data during training is very important. Second, we develop a stacked architecture that includes warping of the second image with intermediate optical flow. Third, we elaborate on small displacements by introducing a subnetwork specializing on small motions. FlowNet 2.0 is only marginally slower than the original FlowNet but decreases the estimation error by more than 50%. It performs on par with state-of-the-art methods, while running at interactive frame rates. Moreover, we present faster variants that allow optical flow computation at up to 140fps with accuracy matching the original FlowNet.

Related Papers

• → Control schemes for synchronizing two subnetworks with weak couplings(2014)5 cited
• → Fast decomposition of networks in minimally interconnected subnetworks(1980)2 cited
• → Finding effective subnetwork markers for cancer by passing messages(2011)
• → Topological conditions for solvability of pseudo-tearing subnetwork(1990)
• → Multi-Objective Approach for Identifying Cancer Subnetwork Markers(2020)