Accurate Optical Flow via Direct Cost Volume Processing

Jia Xu      RenĂ© Ranftl      Vladlen Koltun

Intel Labs

 
sintel-vis.jpg
 

Abstract

We present an optical flow estimation approach that operates on the full four-dimensional cost volume. This direct approach shares the structural benefits of leading stereo matching pipelines, which are known to yield high accuracy. To this day, such approaches have been considered impractical due to the size of the cost volume. We show that the full four-dimensional cost volume can be constructed in a fraction of a second due to its regularity. We then exploit this regularity further by adapting semi-global matching to the four-dimensional setting. This yields a pipeline that achieves significantly higher accuracy than state-of-the-art optical flow methods while being faster than most. Our approach outperforms all published general-purpose optical flow methods on both Sintel and KITTI 2015 benchmarks.


Publication

  • Jia Xu, RenĂ© Ranftl, and Vladlen Koltun. Accurate Optical Flow via Direct Cost Volume Processing. In Computer Vision and Pattern Recognition (CVPR), July 2017. PDF, Poster, Bibtex.

  • Sintel Benchmarking Results (Winner Since 10/2016)

    sintel-table.png

    KITTI 2015 Benchmarking Results

    kitti-table.png

    Source code

    GitHub



    eXTReMe Tracker