A Fast and Lightweight 3D Keypoint Detector

Abstract

Keypoint detection is crucial in many visual tasks, such as object recognition, shape retrieval, and 3D reconstruction, as labeling point data is labor-intensive or sometimes implausible. Nevertheless, it is challenging to quickly and accurately locate keypoints unsupervised from point clouds. This work proposes a fast and lightweight 3D keypoint detector that can efficiently and accurately detect keypoints from point clouds. Our method does not require a complex model learning process and generalizes well to new scenes. Specifically, we consider detecting keypoints a saliency detection problem for a point cloud. First, we propose a simple and effective distance measure to characterize the saliency of points in a point cloud. This distance describes geometrically essential points in the point cloud. Next, we present a regional saliency based on relative centroid distance representation that can globally characterize keypoints with regional visual information. Third, we combine geometric and semantic cues to generate a saliency map of the point cloud for determining stable 3D keypoints. We evaluate our method against existing approaches on four benchmark keypoint datasets to demonstrate its state-of-the-art performance.