2.3k citations · 3.3k across the 4 of their papers we have counts for
4 papers
What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
Nikolaus Mayer, Eddy Ilg, Philipp Fischer +4
The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations. As a…
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Eddy Ilg, Nikolaus Mayer, Tonmoy Saikia +3
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…
DeMoN: Depth and Motion Network for Learning Monocular Stereo
Benjamin Ummenhofer, Huizhong Zhou, Jonas Uhrig +4
In this paper we formulate structure from motion as a learning problem. We train a convolutional network end-to-end to compute depth and camera motion from successive, unconstraine…
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
Nikolaus Mayer, Eddy Ilg, Philip Häusser +4
Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-ca…