 |
    |
Dense Semi-rigid Scene Flow Estimation from RGBD Images*
Julian Quiroga1, 3, Thomas Brox2, Frédéric Devernay1, and James Crowley1
1PRIMA team, INRIA, Grenoble, France
Julian.Quiroga@inria.fr
Frederic.Devernay@inria.fr
James.Crowley@inria.fr
2Department of Computer Science, University of Freiburg, Germany
brox@cs.uni-freiburg.de
3Departamento de Electrónica, Pontificia Universidad Javeriana, Colombia
Abstract. Scene flow is defined as the motion field in 3D space, and can be computed from a single view when using an RGBD sensor. We propose a new scene flow approach that exploits the local and piecewise rigidity of real world scenes. By modeling the motion as a field of twists, our method encourages piecewise smooth solutions of rigid body motions. We give a general formulation to solve for local and global rigid motions by jointly using intensity and depth data. In order to deal efficiently with a moving camera, we model the motion as a rigid component plus a non-rigid residual and propose an alternating solver. The evaluation demonstrates that the proposed method achieves the best results in the most commonly used scene flow benchmark. Through additional experiments we indicate the general applicability of our approach in a variety of different scenarios.
Keywords: motion, scene flow, RGBD image
*This work was supported by a collaborative research program between Inria Grenoble and University of Freiburg. We gratefully acknowledge partial funding by CMIRA 2013 (Region Rhône-Alpes), GDR ISIS (CNRS), and COLCIENCIAS (Colombia).
LNCS 8695, p. 567 ff.
lncs@springer.com
© Springer International Publishing Switzerland 2014