Dense Semi-Rigid Scene Flow Estimation from RGBD images ⋆

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 piece-wise 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 effi-ciently with a moving camera, we model the motion as a rigid component plus a non-rigid residual and propose an alternating solver. The evalu-ation 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