Abstract
Modern optical flow methods are often composed of a cascade of many independent steps or formulated as a black box neural network that is hard to interpret and analyze. In this work we seek for a plain, interpretable, but learnable solution. We propose a novel inpainting based algorithm that approaches the problem in three steps: feature selection and matching, selection of supporting points and energy based inpainting. To facilitate the inference we propose an optimization layer that allows to backpropagate through 10K iterations of a first-order method without any numerical or memory problems. Compared to recent state-of-the-art networks, our modular CNN is very lightweight and competitive with other, more involved, inpainting based methods.
Supported by the ERC starting grant 640156, ‘HOMOVIS’.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Susstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34, 2274–2282 (2012)
Agresti, G., Minto, L., Marin, G., Zanuttigh, P.: Deep learning for confidence information in stereo and tof data fusion. In: The IEEE International Conference on Computer Vision (ICCV) Workshops, October 2017
Barron, J.T., Poole, B.: The fast bilateral solver. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 617–632. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_38
Beck, A., Teboulle, M.: SIAM J. Imaging Sci. A fast iterative shrinkage-thresholding algorithm for linear inverse problems 2, 183–202 (2009)
Bredies, K., Kunisch, K., Pock, T.: SIAM J. Imaging Sci. Total generalized variation 3, 492–526 (2010)
Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-24673-2_3
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
Chen, T., Xu, B., Zhang, C., Guestrin, C.: Training deep nets with sublinear memory cost. CoRR abs/1604.06174 (2016)
Chen, Y., Ranftl, R., Pock, T.: A bi-level view of inpainting - based image compression. CoRR abs/1401.4112 (2014)
Dollár, P., Zitnick, C.L.: Structured forests for fast edge detection. In: CVPR, ICCV 2013, pp. 1841–1848. IEEE (2013)
Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: ICCV (2015)
Galić, I., Weickert, J., Welk, M., Bruhn, A., Belyaev, A., Seidel, H.P.: Image compression with anisotropic diffusion. J. Math. Imaging Vis. 31(2), 255–269 (2008). https://doi.org/10.1007/s10851-008-0087-0
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? In: CVPR (2012)
Griewank, A., Walther, A.: Algorithm 799: revolve: an implementation of checkpointing for the reverse or adjoint mode of computational differentiation. ACM Trans. Math. Softw. 26(1), 19–45 (2000)
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
Hu, X., Mordohai, P.: A quantitative evaluation of confidence measures for stereo vision. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2121–2133 (2012)
Hu, Y., Li, Y., Song, R.: Robust interpolation of correspondences for large displacement optical flow. In: CVPR. IEEE (2017)
Hu, Y., Song, R., Li, Y.: Efficient coarse-to-fine patchmatch for large displacement optical flow. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016
Hu, Y., Song, R., Li, Y.: Efficient coarse-to-fine patchmatch for large displacement optical flow. In: CVPR. IEEE (2016)
Hui, T.W., Tang, X., Change Loy, C.: Liteflownet: a lightweight convolutional neural network for optical flow estimation. In: CVPR (2018)
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)
Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: CVPR (2015)
Munda, G., Shekhovtsov, A., Knöbelreiter, P., Pock, T.: Scalable full flow with learned binary descriptors. In: Roth, V., Vetter, T. (eds.) GCPR 2017. LNCS, vol. 10496, pp. 321–332. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66709-6_26
Nesterov, Y.: A method of solving a convex programming problem with convergence rate O(\(\frac{1}{k^2}\)). Sov. Math. Dokl. 27 (1983)
Peter, P., Hoffmann, S., Nedwed, F., Hoeltgen, L., Weickert, J.: From optimised inpainting with linear PDEs towards competitive image compression codecs. In: Bräunl, T., McCane, B., Rivera, M., Yu, X. (eds.) PSIVT 2015. LNCS, vol. 9431, pp. 63–74. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-29451-3_6
Poggi, M., Tosi, F., Mattoccia, S.: Quantitative evaluation of confidence measures in a machine learning world. In: ICCV, October 2017
Ranjan, A., Black, M.J.: Optical flow estimation using a spatial pyramid network. In: CVPR (2017)
Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Epicflow: edge-preserving interpolation of correspondences for optical flow. In: CVPR. IEEE (2015)
Rhemann, C., Hosni, A., Bleyer, M., Rother, C., Gelautz, M.: Fast cost-volume filtering for visual correspondence and beyond. In: CVPR, pp. 3017–3024. IEEE (2011)
Riegler, G., Rüther, M., Bischof, H.: ATGV-Net: accurate depth super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 268–284. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_17
Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Phys. D Nonlinear Phenom. 60, 259–268 (1992)
Sun, D., Yang, X., Liu, M.Y., Kautz, J.: PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In: CVPR (2018)
Theano Development Team: Theano: a Python framework for fast computation of mathematical expressions. CoRR (2016)
Vogel, C., Pock, T.: A primal dual network for low-level vision problems. In: Roth, V., Vetter, T. (eds.) GCPR 2017. LNCS, vol. 10496, pp. 189–202. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66709-6_16
Wang, S., Fanello, S.R., Rhemann, C., Izadi, S., Kohli, P.: The global patch collider. In: CVPR. IEEE, July 2016
Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: DeepFlow: large displacement optical flow with deep matching. In: ICCV. IEEE, Sydney, December 2013
Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., Bischof, H.: Anisotropic Huber-L1 optical flow. In: BMVC (2009)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR (2016)
Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: ICCV (2015)
Zweig, S., Wolf, L.: InterpoNet, a brain inspired neural network for optical flow dense interpolation. In: CVPR, pp. 6363–6372 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Vogel, C., Knöbelreiter, P., Pock, T. (2019). Learning Energy Based Inpainting for Optical Flow. In: Jawahar, C., Li, H., Mori, G., Schindler, K. (eds) Computer Vision – ACCV 2018. ACCV 2018. Lecture Notes in Computer Science(), vol 11366. Springer, Cham. https://doi.org/10.1007/978-3-030-20876-9_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-20876-9_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20875-2
Online ISBN: 978-3-030-20876-9
eBook Packages: Computer ScienceComputer Science (R0)