Efficient dense 3D scene flow from sparse or dense stereo data

A. Wedel, C. Rabe, T. Vaudrey, Thomas Brox, U. Franke, D. Cremers
European Conference on Computer Vision (ECCV), Springer, LNCS, Vol.5302: 739-751, Oct. 2008
Abstract: This paper presents a technique for estimating the threedimensional velocity vector field that describes the motion of each visible scene point (scene flow). The technique presented uses two consecutive image pairs from a stereo sequence. The main contribution is to decouple the position and velocity estimation steps, and to estimate dense velocities using a variational approach. We enforce the scene flow to yield consistent displacement vectors in the left and right images. The decoupling strategy has two main advantages: Firstly, we are independent in choosing a disparity estimation technique, which can yield either sparse or dense correspondences, and secondly, we can achieve frame rates of 5 fps on standard consumer hardware. The approach provides dense velocity estimates with accurate results at distances up to 50 meters.

Other associated files : wedel_eccv08.pdf [9.5MB]  

Images and movies


BibTex reference

  author       = "A. Wedel and C. Rabe and T. Vaudrey and T. Brox and U. Franke and D. Cremers",
  title        = "Efficient dense 3D scene flow from sparse or dense stereo data",
  booktitle    = "European Conference on Computer Vision (ECCV)",
  series       = "Lecture Notes in Computer Science",
  volume       = "5302",
  pages        = "739-751",
  month        = "Oct.",
  year         = "2008",
  publisher    = "Springer",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2008/Bro08a"

Other publications in the database