This paper presents a novel method for recognizing free-form 3D objects in point clouds. Unlike traditional approaches that rely on local point descriptors, the proposed method creates a global model description based on oriented point pair features and matches it using a fast voting scheme. The global model description consists of all model point pair features and represents a mapping from the point pair feature space to the model, where similar features on the model are grouped together. This representation allows the use of much sparser object and scene point clouds, resulting in very fast performance. Recognition is done locally using an efficient voting scheme on a reduced two-dimensional search space. The method is tested on synthetic and real datasets, demonstrating its efficiency and high recognition performance in the presence of noise, clutter, and partial occlusions. Compared to state-of-the-art approaches, the proposed method achieves better recognition rates and is significantly faster. The method creates a global model description using oriented point pair features and matches it using a fast voting scheme. The point pair feature describes the relative position and orientation of two oriented points. The global model description is a mapping from the sampled point pair feature space to the model. The voting scheme is used to optimize the model pose in a locally reduced search space. The method is efficient and accurate, allowing for fast and reliable recognition of free-form 3D objects in point clouds. The results show that the method outperforms existing approaches in terms of recognition rate and efficiency.This paper presents a novel method for recognizing free-form 3D objects in point clouds. Unlike traditional approaches that rely on local point descriptors, the proposed method creates a global model description based on oriented point pair features and matches it using a fast voting scheme. The global model description consists of all model point pair features and represents a mapping from the point pair feature space to the model, where similar features on the model are grouped together. This representation allows the use of much sparser object and scene point clouds, resulting in very fast performance. Recognition is done locally using an efficient voting scheme on a reduced two-dimensional search space. The method is tested on synthetic and real datasets, demonstrating its efficiency and high recognition performance in the presence of noise, clutter, and partial occlusions. Compared to state-of-the-art approaches, the proposed method achieves better recognition rates and is significantly faster. The method creates a global model description using oriented point pair features and matches it using a fast voting scheme. The point pair feature describes the relative position and orientation of two oriented points. The global model description is a mapping from the sampled point pair feature space to the model. The voting scheme is used to optimize the model pose in a locally reduced search space. The method is efficient and accurate, allowing for fast and reliable recognition of free-form 3D objects in point clouds. The results show that the method outperforms existing approaches in terms of recognition rate and efficiency.