Abstract
Two optical flow estimation problems are addressed: (i) occlusion estimation and handling, and (ii) estimation from image sequences longer than two frames. The proposed ContinualFlow method estimates occlusions before flow, avoiding the use of flow corrupted by occlusions for their estimation. We show that providing occlusion masks as an additional input to flow estimation improves the standard performance metric by more than 25% on both KITTI and Sintel. As a second contribution, a novel method for incorporating information from past frames into flow estimation is introduced. The previous frame flow serves as an input to occlusion estimation and as a prior in occluded regions, i.e. those without visual correspondences. By continually using the previous frame flow, ContinualFlow performance improves further by 18% on KITTI and 7% on Sintel, achieving top performance on KITTI and Sintel.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
As of the submission date, July 7, 2018.
- 2.
The “Final pass” category.
- 3.
Excluding scene flow methods.
- 4.
As of July 7, 2018.
References
Bailer, C., Taetz, B., Stricker, D.: Flow fields: dense correspondence fields for highly accurate large displacement optical flow estimation. In: ICCV (2015)
Bailer, C., Varanasi, K., Stricker, D.: CNN-based patch matching for optical flow with thresholded hinge embedding loss. In: CVPR, pp. 3250–3259 (2017)
Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. IJCV (2011). https://doi.org/10.1007/s11263-010-0390-2
Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: International Conference on Machine Learning, pp. 41–48. ACM (2009)
Black, M.J., Anandan, P.: Robust dynamic motion estimation over time. In: CVPR (1991)
Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 611–625. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33783-3_44
Caelles, S., Maninis, K.K., Pont-Tuset, J., Leal-Taixé, L., Cremers, D., Van Gool, L.: One-shot video object segmentation. In: CVPR 2017. IEEE (2017)
Chen, Q., Koltun, V.: Full flow: optical flow estimation by global optimization over regular grids. In: CVPR (2016)
Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: ICCV, pp. 2758–2766, December 2015
Gaidon, A., Wang, Q., Cabon, Y., Vig, E.: Virtual worlds as proxy for multi-object tracking analysis. In: CVPR (2016)
Garg, R., Pizarro, L., Rueckert, D., Agapito, L.: Dense multi-frame optic flow for non-rigid objects using subspace constraints. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, vol. 6495, pp. 460–473. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-19282-1_37
Garg, R., Roussos, A., Agapito, L.: A variational approach to video registration with subspace constraints. IJCV 104(3), 286–314 (2013)
Güney, F., Geiger, A.: Deep discrete flow. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10114, pp. 207–224. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-54190-7_13
Horn, B.K., Schunck, B.G.: Determining optical flow. Artif. Intell. 17(1–3), 185–203 (1981)
Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely connected convolutional networks. In: CVPR (2017)
Hui, T.W., Tang, X., Loy, C.C.: LiteFlowNet: a lightweight convolutional neural network for optical flow estimation. In: CVPR, June 2018
Hur, J., Roth, S.: MirrorFlow: exploiting symmetries in joint optical flow and occlusion estimation. ICCV (2017)
Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: CVPR (2017)
Irani, M.: Multi-frame correspondence estimation using subspace constraints. IJCV 48(3), 173–194 (2002)
Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. In: ANIPS (2015)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Kondermann, D., et al.: The HCI benchmark suite: stereo and flow ground truth with uncertainties for urban autonomous driving. In: CVPR (2016)
Maurer, D., Bruhn, A.: ProFlow: learning to predict optical flow. In: BMVC (2018)
Mayer, N., et al.: What makes good synthetic training data for learning disparity and optical flow estimation? IJCV 126(9), 942–960 (2018)
Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: CVPR (2016)
Meister, S., Hur, J., Roth, S.: UnFlow: unsupervised learning of optical flow with a bidirectional census loss. In: AAAI (2018)
Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: CVPR (2015)
Murray, D.W., Buxton, B.F.: Scene segmentation from visual motion using global optimization. PAMI 9, 220–228 (1987)
Pang, J., Sun, W., Ren, J.S., Yang, C., Yan, Q.: Cascade residual learning: a two-stage convolutional neural network for stereo matching. In: CVPR (2017)
Pérez, J.S., Meinhardt-Llopis, E., Facciolo, G.: TV-L1 optical flow estimation. Image Process. Line 3, 137–150 (2013)
Ranjan, A., Black, M.J.: Optical flow estimation using a spatial pyramid network. In: CVPR (2018)
Robust vision challenge team: robust vision challenge (2018). http://www.robustvision.net. Accessed 8 July 2018
Schuster, R., Bailer, C., Wasenmüller, O., Stricker, D.: FlowFields++: accurate optical flow correspondences meet robust interpolation. In: ICIP (2018)
Sun, D., Liu, C., Pfister, H.: Local layering for joint motion estimation and occlusion detection. In: CVPR, pp. 1098–1105 (2014)
Sun, D., Yang, X., Liu, M.Y., Kautz, J.: PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In: CVPR (2018)
Sundaram, N., Brox, T., Keutzer, K.: Dense point trajectories by GPU-accelerated large displacement optical flow. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 438–451. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15549-9_32
Unger, M., Werlberger, M., Pock, T., Bischof, H.: Joint motion estimation and segmentation of complex scenes with label costs and occlusion modeling. In: CVPR, pp. 1878–1885. IEEE (2012)
Volz, S., Bruhn, A., Valgaerts, L., Zimmer, H.: Modeling temporal coherence for optical flow. In: ICCV (2011)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: DeepFlow: large displacement optical flow with deep matching. In: ICCV (2013)
Wulff, J., Sevilla-Lara, L., Black, M.J.: Optical flow in mostly rigid scenes. In: CVPR (2017)
Xiao, J., Cheng, H., Sawhney, H., Rao, C., Isnardi, M.: Bilateral filtering-based optical flow estimation with occlusion detection. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 211–224. Springer, Heidelberg (2006). https://doi.org/10.1007/11744023_17
Xie, S., Tu, Z.: Holistically-nested edge detection. In: ICCV, pp. 1395–1403 (2015)
Acknowledgements
The research was supported by Toyota Motor Europe, CTU student grant SGS17/185/OHK3/3T/13 and the OP VVV MEYS project CZ.02.1.01/0.0/0.0/16_019/0000765 Research Center for Informatics.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Neoral, M., Šochman, J., Matas, J. (2019). Continual Occlusion and Optical Flow Estimation. In: Jawahar, C., Li, H., Mori, G., Schindler, K. (eds) Computer Vision – ACCV 2018. ACCV 2018. Lecture Notes in Computer Science(), vol 11364. Springer, Cham. https://doi.org/10.1007/978-3-030-20870-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-20870-7_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20869-1
Online ISBN: 978-3-030-20870-7
eBook Packages: Computer ScienceComputer Science (R0)