A Naturalistic Open Source Movie for Optical Flow Evaluation

@inproceedings{Butler2012ANO,
  title={A Naturalistic Open Source Movie for Optical Flow Evaluation},
  author={Daniel J. Butler and Jonas Wulff and Garrett B. Stanley and Michael J. Black},
  booktitle={ECCV},
  year={2012}
}
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… CONTINUE READING
BETA

Citations

Publications citing this paper.
SHOWING 1-10 OF 544 CITATIONS, ESTIMATED 39% COVERAGE

FILTER CITATIONS BY YEAR

2012
2019

CITATION STATISTICS

  • 147 Highly Influenced Citations

  • Averaged 131 Citations per year over the last 3 years

  • 20% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 17 REFERENCES

Producer): Sintel

  • T. Roosendaal
  • Blender Foundation, Durian Open Movie Project
  • 2010
Highly Influential
8 Excerpts

Similar Papers

Loading similar papers…