RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor
This addresses the bottleneck of computational efficiency in point cloud registration for applications like autonomous driving and robotics, representing a strong incremental improvement.
The paper tackles the problem of inefficient keypoint detection and description for large-scale point cloud registration by proposing RSKDD-Net, which uses random sampling and a learning-based approach to achieve state-of-the-art performance with over 15 times faster speed than existing methods.
Keypoint detector and descriptor are two main components of point cloud registration. Previous learning-based keypoint detectors rely on saliency estimation for each point or farthest point sample (FPS) for candidate points selection, which are inefficient and not applicable in large scale scenes. This paper proposes Random Sample-based Keypoint Detector and Descriptor Network (RSKDD-Net) for large scale point cloud registration. The key idea is using random sampling to efficiently select candidate points and using a learning-based method to jointly generate keypoints and descriptors. To tackle the information loss of random sampling, we exploit a novel random dilation cluster strategy to enlarge the receptive field of each sampled point and an attention mechanism to aggregate the positions and features of neighbor points. Furthermore, we propose a matching loss to train the descriptor in a weakly supervised manner. Extensive experiments on two large scale outdoor LiDAR datasets show that the proposed RSKDD-Net achieves state-of-the-art performance with more than 15 times faster than existing methods. Our code is available at https://github.com/ispc-lab/RSKDD-Net.