swMATH ID: 31203
Software Authors: E. Ilg, N. Mayer, T. Saikia, M. Keuper, A. Dosovitskiy, T. Brox
Description: FlowNet 2.0: Evolution of optical flow estimationwith deep networks. 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 sub-network specializing on small motions. FlowNet 2.0 is only marginally slower than the original FlowNet but decreases the estimation error by more than 50
Homepage: https://arxiv.org/abs/1612.01925
Source Code:  https://github.com/lmb-freiburg/flownet2
Keywords: Computer Vision; Pattern Recognition; arXiv_cs.CV; Optical Flow Estimation; Deep Networks; FlowNet
Related Software: Adam; EpicFlow; PWC-Net; KITTI; DeepFlow; TensorFlow; ImageNet; PointNet; UCF101; PyTorch; Key.Net; U-Net; MVSNet; BRISK; SOSNet; L2-Net; Theia; R2D2; SuperGlue; Pfinder
Cited in: 17 Publications

Standard Articles

1 Publication describing the Software Year
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
E. Ilg, N. Mayer, T. Saikia, M. Keuper, A. Dosovitskiy, T. Brox

Citations by Year