Abstract
Convolutional neural networks (CNNs) have been successfully applied to optical flow estimation and outperformed a number of variational approaches. The spatial pyramid network (SPyNet) is one of these CNN based approaches which is efficient to estimate optical flow. In this paper, a deeper spatial pyramid network (DSPyNet) is proposed based on SPyNet. In DSPyNet, the network architecture of SPyNet is reused and further refined at each pyramid level by convolutional factorization, and an addition of inception module and \(1\times 1\) convolutional operation is further used to enhance visual representation. Moreover, since bilinear interpolation reduces the quality of up-sampled flow field due to its low-pass filtering property, it is replaced with small kernel convolutional operations like image super-resolution using CNNs. The proposed DSPyNet is evaluated on several optical flow estimation benchmark datasets and the experimental results verify its effectiveness.
This work was supported in part by National Natural Science Foundation of China under Grants 61622115 and 61472281, Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning (No. GZ2015005), Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing (17DZ2251600), and IBM Shared University Research Awards Program.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. Int. J. Comput. Vis. 92(1), 1–31 (2011)
Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: Proceedings of the European Conference on Computer Vision, pp. 611–625, October 2012
Dosovitskiy, A., Fischery, P., Ilg, E., Hausser, P.: Flownet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2758–2766, December 2015
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354–3361, June 2012
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the International Conference on Artificial Intelligence and Statistics, pp. 315–323, April 2011
Han, D.: Comparison of commonly used image interpolation methods. In: Proceedings of the International Conference on Computer Science and Electronics Engineerings, pp. 1556–1559, March 2013
Horn, B.K., Schunck, B.G.: Determining optical flow. Artif. Intell. 17(1–3), 185–203 (1981)
Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: Flownet 2.0: evolution of optical flow estimation with deep networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2462–2470, December 2017
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Proceedings of the International Conference on Neural Information Processing Systems, pp. 1097–1105, December 2012
Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)
Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4040–4048, June 2016
Ranjan, A., Black, M.J.: Optical flow estimation using a spatial pyramid network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2720–2729, June 2017
Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640–651 (2016)
Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874–1883, June 2016
Sun, D., Roth, S., Black, M.J.: A quantitative analysis of current practices in optical flow estimation and the principles behind them. Int. J. Comput. Vision 106(2), 115–137 (2014)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826, June 2016
Toshev, A., Szegedy, C.: Deeppose: human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1653–1660, June 2014
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Sun, Z., Wang, H. (2018). Deeper Spatial Pyramid Network with Refined Up-Sampling for Optical Flow Estimation. In: Hong, R., Cheng, WH., Yamasaki, T., Wang, M., Ngo, CW. (eds) Advances in Multimedia Information Processing – PCM 2018. PCM 2018. Lecture Notes in Computer Science(), vol 11164. Springer, Cham. https://doi.org/10.1007/978-3-030-00776-8_45
Download citation
DOI: https://doi.org/10.1007/978-3-030-00776-8_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00775-1
Online ISBN: 978-3-030-00776-8
eBook Packages: Computer ScienceComputer Science (R0)