Graph-Based Deformable 3D Object Matching

Abstract. We present a method for efficient detection of deformed 3D objects in 3D point clouds that can handle large amounts of clutter, noise, and occlu-sion. The method generalizes well to different object classes and does not require an explicit deformation model. Instead, deformations are learned based on a few registered deformed object instances. The approach builds upon graph match-ing to find correspondences between scene and model points. The robustness is increased through a parametrization where each graph vertex represents a full rigid transformation. We speed up the matching through greedy multi-step graph pruning and a constant-time feature matching. Quantitative and qualitative exper-iments demonstrate that our method is robust, efficient, able to detect rigid and non-rigid objects and exceeds state of the art.