Philipp Fischer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Philipp Fischer has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Alexey Dosovitskiy
University of Freiburg Technical University of Munich
3 shared publications - Thomas Brox
University of Freiburg
3 shared publications - Eddy Ilg
University of Freiburg Germany
2 shared publications - Nikolaus Mayer
University of Freiburg Technical University of Munich
2 shared publications - Caner Hazirbas
University of Freiburg Technical University of Munich
1 shared publication - Daniel Cremers
Technical University of Munich
1 shared publication
Latest Publications
- 2 April 2018
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 126 (9) , 942-960
What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
- 2 April 2018
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 126 (9) , 942-960
What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
- Open Access
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
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-called FlowNet was enabled by a large synthetically generated dataset. The present paper extends the concept of optical flow estimation via convolutional networks to disparity and scene flow estimation. To this end, we propose three synthetic stereo video datasets with sufficient realism, variation, and size to successfully train large networks. Our datasets are the first large-scale datasets to enable training and evaluating scene flow methods. Besides the datasets, we present a convolutional network for real-time disparity estimation that provides state-of-the-art results. By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.
Open AccessA Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
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-called FlowNet was enabled by a large synthetically generated dataset. The present paper extends the concept of optical flow estimation via convolutional networks to disparity and scene flow estimation. To this end, we propose three synthetic stereo video datasets with sufficient realism, variation, and size to successfully train large networks. Our datasets are the first large-scale datasets to enable training and evaluating scene flow methods. Besides the datasets, we present a convolutional network for real-time disparity estimation that provides state-of-the-art results. By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.
- Open Access
- 3 November 2015
- Published by Springer Nature
- p. 368-378
Image Orientation Estimation with Convolutional Networks
- 3 November 2015
- Published by Springer Nature
- p. 368-378
Open AccessImage Orientation Estimation with Convolutional Networks
- 15 October 2014
- Published by Springer Nature
- p. 239-249
Image Descriptors Based on Curvature Histograms
- 15 October 2014
- Published by Springer Nature
- p. 239-249
Image Descriptors Based on Curvature Histograms