GraphFlow - 6D Large Displacement Scene Flow via Graph Matching
نویسندگان
چکیده
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.
منابع مشابه
Estimations simultanées du flot de scène et d’occultations par un système d’EDP Simultaneous scene flow and occlusions estimations by using a common PDE framework
This paper presents a method for scene flow estimation from a calibrated stereo image sequence. The scene flow contains the 3-D displacement field of scene points, so that the 2-D optical flow can be seen as a projection of the scene flow onto the images. We propose to recover the scene flow by coupling the optical flow estimation in both cameras with dense stereo matching between the images, t...
متن کاملBounding cochordal cover number of graphs via vertex stretching
It is shown that when a special vertex stretching is applied to a graph, the cochordal cover number of the graph increases exactly by one, as it happens to its induced matching number and (Castelnuovo-Mumford) regularity. As a consequence, it is shown that the induced matching number and cochordal cover number of a special vertex stretching of a graph G are equal provided G is well-covered bipa...
متن کاملStructure guided interior scene synthesis via graph matching
We present a method for reshuffle-based 3D interior scene synthesis guided by scene structures. Given several 3D scenes, we form each 3D scene as a structure graph associated with a relationship set. Considering both the object similarity and relation similarity, we then establish a furniture-object-based matching between scene pairs via graph matching. Such a matching allows us to merge the st...
متن کاملShape and Motion Carving in 6D
The motion of a non-rigid scene over time imposes more constraints on its structure than those derived from images at a single time instant alone. An algorithm is presented for simultaneously recovering dense scene shape and scene flow (i.e., the instantaneous 3D motion at every point in the scene). The algorithm operates by carving away hexels, or points in the 6D space of all possible shapes ...
متن کاملMatching Features from Edge-Processed Image Sequences
This paper discusses the problem of matching two edge-vertex lists, extracted from two similar images after edge processing. The matching is intended to provide feature-flow information for a Structure From Motion algorithm. The matching is primarily via vertices, but the topology of the structures is used to ensure consistent vertex matches, and to achieve matching of complete edges. Results a...
متن کامل