Efficient Dense Scene Flow from Sparse or Dense Stereo Data

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.

• Type: Conference
• Year: 2008
• Where: ECCV
• Authors: Andreas Wedel, Clemens Rabe, Tobi Vaudrey, Thomas Brox, Uwe Franke, Daniel Cremers
• Keywords: Computer Vision, Dense Velocities, Dense Velocity Estimates, Disparity Estimation Technique, ECCV 2008, Threedimensional Velocity Vector, Velocity Estimation Steps