GraphFlow – 6D Large Displacement Scene Flow via Graph Matching
Hassan Abu Alhaija, Anita Sellent, Daniel Kondermann, Carsten Rother · Lecture notes in computer science · 2015
We present an approach for computing dense scene flow from two large displacement RGB-D images. When dealing with large displacements the crucial step is to estimate the overall motion correctly. While state-of-the-art approaches focus on RGB information to establish guiding correspondences, we explore the power of depth edges. To achieve this, we present a new graph matching technique that brings sparse depth edges into correspondence. An additional contribution is the formulation of a continuous-label energy which is used to densify the sparse graph matching output. We present results on challenging Kinect images, for which we outperform state-of-the-art techniques. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.