Accurate Optical Flow via Direct Cost Volume Processing
Jia Xu, Ren\'e Ranftl, Vladlen Koltun

TL;DR
This paper introduces a novel optical flow estimation method that directly processes the full four-dimensional cost volume, achieving higher accuracy and faster performance than existing methods by leveraging the regularity of the cost volume.
Contribution
It presents a practical approach to construct and utilize the full 4D cost volume for optical flow, significantly improving accuracy and speed over prior techniques.
Findings
Outperforms all published general-purpose optical flow methods on Sintel and KITTI 2015.
Constructs the full 4D cost volume in a fraction of a second.
Achieves higher accuracy while maintaining faster processing speeds.
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Advanced Image Processing Techniques · Optical Coherence Tomography Applications
