Real-time Halfway Domain Reconstruction of Motion and Geometry

Lucas Thies, Michael Zollhöfer, Christian Richardt, Christian Theobalt, Günther Greiner

Research output: Contribution to conferencePaperpeer-review

2 Citations (SciVal)
186 Downloads (Pure)


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.
Original languageEnglish
Number of pages10
Publication statusPublished - 25 Oct 2016
EventInternational Conference on 3D Vision - Stanford University, Palo Alto, USA United States
Duration: 25 Oct 201628 Oct 2016


ConferenceInternational Conference on 3D Vision
Abbreviated title3DV
Country/TerritoryUSA United States
CityPalo Alto
Internet address


Dive into the research topics of 'Real-time Halfway Domain Reconstruction of Motion and Geometry'. Together they form a unique fingerprint.

Cite this