Abstract | ||
---|---|---|
We present a novel approach for real-time joint reconstruction of 3D scene motion and geometry from binocular stereo videos. Our approach is based on a novel variational halfway-domain scene flow formulation, which allows us to obtain highly accurate spatiotemporal reconstructions of shape and motion. We solve the underlying optimization problem at real-time frame rates using a novel data-parallel robust non-linear optimization strategy. Fast convergence and large displacement flows are achieved by employing a novel hierarchy that stores delta flows between hierarchy levels. High performance is obtained by the introduction of a coarser warp grid that decouples the number of unknowns from the input resolution of the images. We demonstrate our approach in a live setup that is based on two commodity webcams, as well as on publicly available video data. Our extensive experiments and evaluations show that our approach produces high-quality dense reconstructions of 3D geometry and scene flow at real-time frame rates, and compares favorably to the state of the art. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/3DV.2016.55 | 2016 Fourth International Conference on 3D Vision (3DV) |
Keywords | DocType | Volume |
scene flow,stereo reconstruction,motion reconstruction,halfway domain,data-parallel optimization | Conference | abs/1610.07159 |
ISSN | ISBN | Citations |
2378-3826 | 978-1-5090-5408-4 | 1 |
PageRank | References | Authors |
0.34 | 55 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lucas Thies | 1 | 31 | 1.68 |
Michael Zollhöfer | 2 | 852 | 42.25 |
Christian Richardt | 3 | 393 | 26.27 |
Christian Theobalt | 4 | 3211 | 159.16 |
Günther Greiner | 5 | 598 | 80.74 |