Accurate Optical Flow via Direct Cost Volume Processing
This work addresses the problem of accurate and efficient optical flow estimation for computer vision applications, representing a novel method rather than an incremental improvement.
The authors tackled optical flow estimation by directly processing the full four-dimensional cost volume, achieving significantly higher accuracy than state-of-the-art methods on Sintel and KITTI 2015 benchmarks while being faster than most.
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.