Abstract
Ground truth optical flow is difficult to measure in real scenes with natural motion. As a result, optical flow data sets are restricted in terms of size, complexity, and diversity, making optical flow algorithms difficult to train and test on realistic data. We introduce a new optical flow data set derived from the open source 3D animated short film Sintel. This data set has important features not present in the popular Middlebury flow evaluation: long sequences, large motions, specular reflections, motion blur, defocus blur, and atmospheric effects. Because the graphics data that generated the movie is open source, we are able to render scenes under conditions of varying complexity to evaluate where existing flow algorithms fail. We evaluate several recent optical flow algorithms and find that current highly-ranked methods on the Middlebury evaluation have difficulty with this more complex data set suggesting further research on optical flow estimation is needed. To validate the use of synthetic data, we compare the image- and flow-statistics of Sintel to those of real films and videos and show that they are similar. The data set, metrics, and evaluation website are publicly available.
Chapter PDF
Similar content being viewed by others
References
Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M., Szeliski, R.: A database and evaluation methodology for optical flow. IJCV 92, 1–31 (2011)
Roosendaal, T. (Producer): Sintel. Blender Foundation, Durian Open Movie Project (2010), http://www.sintel.org/
Butler, D., Wulff, J., Stanley, G., Black, M.: MPI-Sintel optical flow benchmark: Supplemental material. MPI-IS-TR-006, MPI for Intelligent Systems (2012)
Roth, S., Black, M.: On the spatial statistics of optical flow. IJCV 74, 33–50 (2007)
Field, D.: Relations between the statistics of natural images and the response properties of cortical cells. J. Opt. Soc. Am. A 4, 2379–2394 (1987)
Simoncelli, E., Olshausen, B.: Natural image statistics and neural representation. Annu. Rev. Neurosci. 24, 1193–1216 (2001)
Barron, J., Fleet, D., Beauchemin, S.: Performance of optical flow techniques. IJCV 12, 43–77 (1994)
McCane, B., Novins, K., Crannitch, D., Galvin, B.: On benchmarking optical flow. CVIU 84, 126–143 (2001)
Otte, M., Nagel, H.-H.: Optical Flow Estimation: Advances and Comparisons. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 800, pp. 51–60. Springer, Heidelberg (1994)
Liu, C., Freeman, W., Adelson, E., Weiss, Y.: Human-assisted motion annotation. In: CVPR, pp. 1–8 (2008)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR, pp. 3354–3361 (2012)
Meister, S., Jaehne, B., Kondermann, D.: An outdoor stereo camera system for the generation of real-world benchmark datasets. Opt. Eng. 51, 021107 (2012)
Sun, D., Roth, S., Lewis, J.P., Black, M.J.: Learning Optical Flow. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 83–97. Springer, Heidelberg (2008)
Brox, T., Bregler, C., Malik, J.: Large displacement optical flow: Descriptor matching in variational motion estimation. PAMI 33, 500–513 (2009)
Sun, D., Roth, S., Black, M.: Secrets of optical flow estimation and their principles. In: CVPR, pp. 2432–2439 (2010)
Horn, B., Schunck, B.: Determining optical flow. AIJ 16, 185–203 (1981)
Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., Bischof, H.: Anisotropic Huber-L1 optical flow. In: BMVC, pp. 1–11 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J. (2012). A Naturalistic Open Source Movie for Optical Flow Evaluation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7577. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33783-3_44
Download citation
DOI: https://doi.org/10.1007/978-3-642-33783-3_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33782-6
Online ISBN: 978-3-642-33783-3
eBook Packages: Computer ScienceComputer Science (R0)