A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

Mayer N, Ilg E, Hausser P, Fischer P, Cremers D, Dosovitskiy A, Brox T (2016)

Publication Type: Conference contribution

Publication year: 2016

Journal

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition IEEE Computer Society; 1999

Publisher: IEEE Computer Society

Book Volume: 2016-December

Pages Range: 4040-4048

Conference Proceedings Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Event location: Las Vegas, NV, USA

ISBN: 9781467388504

DOI: 10.1109/CVPR.2016.438

Abstract

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 evaluation of 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.

Involved external institutions

Albert-Ludwigs-Universität Freiburg DE Germany (DE) Technische Universität München (TUM) DE Germany (DE)

How to cite

APA:

Mayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., & Brox, T. (2016). A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 4040-4048). Las Vegas, NV, USA: IEEE Computer Society.

MLA:

Mayer, Nikolaus, et al. "A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation." Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA IEEE Computer Society, 2016. 4040-4048.

BibTeX: Download