 |
    |
A Naturalistic Open Source Movie for Optical Flow Evaluation
Daniel J. Butler1, Jonas Wulff2, Garrett B. Stanley3, and Michael J. Black2
1University of Washington, Seattle, WA, USA
djbutler@cs.washington.edu
2Max-Planck Institute for Intelligent Systems, Tübingen, Germany
jonas.wulff@tuebingen.mpg.de
black@tuebingen.mpg.de
3Georgia Institute of Technology, Atlanta, GA, USA
garrett.stanley@bme.gatech.edu
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.
LNCS 7577, p. 611 ff.
lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012