Lessons and insights from creating a synthetic optical flow benchmark

Authors:
Jonas Wulff;Daniel J. Butler;Garrett B. Stanley;Michael J. Black
Affiliations:
Max-Planck Institute for Intelligent Systems, Tübingen, Germany;University of Washington, Seattle, WA;Georgia Institute of Technology, Atlanta, GA;Max-Planck Institute for Intelligent Systems, Tübingen, Germany
Venue:
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume 2
Year:
2012

Citing 6
Cited 0

Performance of optical flow techniques

International Journal of Computer Vision
On benchmarking optical flow

Computer Vision and Image Understanding - Special issue on empirical evaluation of computer vision algorithms
On the Spatial Statistics of Optical Flow

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
A Database and Evaluation Methodology for Optical Flow

International Journal of Computer Vision
Are we ready for autonomous driving? The KITTI vision benchmark suite

CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
A naturalistic open source movie for optical flow evaluation

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI

Quantified Score

Hi-index	0.00

Visualization

Abstract

With the MPI-Sintel Flow dataset, we introduce a naturalistic dataset for optical flow evaluation derived from the open source CGI movie Sintel. In contrast to the well-known Middlebury dataset, the MPI-Sintel Flow dataset contains longer and more varied sequences with image degradations such as motion blur, defocus blur, and atmospheric effects. Animators use a variety of techniques that produce pleasing images but make the raw animation data inappropriate for computer vision applications if used "out of the box". Several changes to the rendering software and animation files were necessary in order to produce data for flow evaluation and similar changes are likely for future efforts to construct a scientific dataset from an animated film. Here we distill our experience with Sintel into a set of best practices for using computer animation to generate scientific data for vision research.