Advertisement

What Matters in Unsupervised Optical Flow

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12347)

Abstract

We systematically compare and analyze a set of key components in unsupervised optical flow to identify which photometric loss, occlusion handling, and smoothness regularization is most effective. Alongside this investigation we construct a number of novel improvements to unsupervised flow models, such as cost volume normalization, stopping the gradient at the occlusion mask, encouraging smoothness before upsampling the flow field, and continual self-supervision with image resizing. By combining the results of our investigation with our improved model components, we are able to present a new unsupervised flow technique that significantly outperforms the previous unsupervised state-of-the-art and performs on par with supervised FlowNet2 on the KITTI 2015 dataset, while also being significantly simpler than related approaches.

Supplementary material

Supplementary material 1 (mp4 7879 KB)

Supplementary material 2 (mp4 6278 KB)

Supplementary material 3 (mp4 4084 KB)

Supplementary material 4 (mp4 3096 KB)

References

  1. 1.
    Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. IJCV 92, 1–31 (2011)CrossRefGoogle Scholar
  2. 2.
    Barron, J.L., Fleet, D.J., Beauchemin, S.S.: Performance of optical flow techniques. IJCV 12, 43–77 (1994)Google Scholar
  3. 3.
    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_3CrossRefGoogle Scholar
  4. 4.
    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_44CrossRefGoogle Scholar
  5. 5.
    Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: ICCV (2015)Google Scholar
  6. 6.
    Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? In: CVPR. The KITTI Vision Benchmark Suite (2012)Google Scholar
  7. 7.
    Gibson, J.J.: The Perception of the Visual World. Houghton Mifflin, Boston (1950)Google Scholar
  8. 8.
    Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: ICCV (2019)Google Scholar
  9. 9.
    Gordon, A., Li, H., Jonschkowski, R., Angelova, A.: Depth from videos in the wild: unsupervised monocular depth learning from unknown cameras. In: ICCV (2019)Google Scholar
  10. 10.
    Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artif. Intell. (1981)Google Scholar
  11. 11.
    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)Google Scholar
  12. 12.
    Janai, J., Güney, F., Ranjan, A., Black, M.J., Geiger, A.: Unsupervised learning of multi-frame optical flow with occlusions. In: ECCV (2018)Google Scholar
  13. 13.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)Google Scholar
  14. 14.
    Liu, P., King, I., Lyu, M.R., Xu, J.: DDFlow: learning optical flow with unlabeled data distillation. In: AAAI (2019)Google Scholar
  15. 15.
    Liu, P., Lyu, M.R., King, I., Xu, J.: Selflow: self-supervised learning of optical flow. In: CVPR (2019)Google Scholar
  16. 16.
    Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: DARPA Image Understanding Workshop (1981)Google Scholar
  17. 17.
    Mayer, N., et al.: What makes good synthetic training data for learning disparity and optical flow estimation? IJCV 126, 942–960 (2018)CrossRefGoogle Scholar
  18. 18.
    Meister, S., Hur, J., Roth, S.: Unflow: unsupervised learning of optical flow with a bidirectional census loss. In: AAAI (2018)Google Scholar
  19. 19.
    Menze, M., Heipke, C., Geiger, A.: Joint 3d estimation of vehicles and scene flow. In: ISPRS Workshop on Image Sequence Analysis (2015)Google Scholar
  20. 20.
    Ranjan, A., Black, M.J.: Optical flow estimation using a spatial pyramid network. In: CVPR (2017)Google Scholar
  21. 21.
    Ranjan, A., et al.: Competitive collaboration: joint unsupervised learning of depth, camera motion, optical flow and motion segmentation. In: CVPR (2019)Google Scholar
  22. 22.
    Ren, Z., Yan, J., Ni, B., Liu, B., Yang, X., Zha, H.: Unsupervised deep learning for optical flow estimation. AAAI (2017)Google Scholar
  23. 23.
    Rocco, I., Arandjelovic, R., Sivic, J.: Convolutional neural network architecture for geometric matching. In: CVPR (2017)Google Scholar
  24. 24.
    Sun, D., Roth, S., Black, M.J.: Secrets of optical flow estimation and their principles. In: CVPR (2010)Google Scholar
  25. 25.
    Sun, D., Yang, X., Liu, M.-Y., Kautz, J.: PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In: CVPR (2018)Google Scholar
  26. 26.
    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_32CrossRefGoogle Scholar
  27. 27.
    Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: ICCV (1998)Google Scholar
  28. 28.
    Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR (2011)Google Scholar
  29. 29.
    Wang, Y., Wang, P., Yang, Z., Luo, C., Yang, Y., Xu, W.: UnOS: unified unsupervised optical-flow and stereo-depth estimation by watching videos. In: CVPR (2019)Google Scholar
  30. 30.
    Wang, Y., Yang, Y., Yang, Z., Zhao, L., Wang, P., Xu, W.: Occlusion aware unsupervised learning of optical flow. In: CVPR (2018)Google Scholar
  31. 31.
    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, 600–612 (2004)CrossRefGoogle Scholar
  32. 32.
    Yang, G., Ramanan, D.: Volumetric correspondence networks for optical flow. In: NeurIPS (2019)Google Scholar
  33. 33.
    Yin, Z., Shi, J.: GeoNet: unsupervised learning of dense depth, optical flow and camera pose. In: CVPR (2018)Google Scholar
  34. 34.
    Yu, J.J., Harley, A.W., Derpanis, K.G.: Back to basics: unsupervised learning of optical flow via brightness constancy and motion smoothness. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 3–10. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-49409-8_1CrossRefGoogle Scholar
  35. 35.
    Zhong, Y., Ji, P., Wang, J., Dai, Y., Li, H.: Unsupervised deep epipolar flow for stationary or dynamic scenes. In: CVPR (2019)Google Scholar
  36. 36.
    Zou, Y., Luo, Z., Huang, J.-B.: DF-Net: unsupervised joint learning of depth and flow using cross-task consistency. In: ECCV (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Robotics at GoogleMountain ViewUSA
  2. 2.Google AIMountain ViewUSA

Personalised recommendations