PinNet: Keypoint-Aware Learned Local Descriptors with Geometric Embedding for Loop Closure in LiDAR SLAM

Yanlong Ma; Nakul S. Joshi; Christa S. Robison; Philip R. Osteen; Brett T. Lopez

PinNet: Keypoint-Aware Learned Local Descriptors with Geometric Embedding for Loop Closure in LiDAR SLAM

Robotics 2026-06-26 v1

Authors: Yanlong Ma , Nakul S. Joshi , Christa S. Robison , Philip R. Osteen , Brett T. Lopez

Abstract

Loop closure is essential to reduce drift and build globally consistent maps in large-scale environments. However, reliable loop closure with only geometric information from, e.g., a LiDAR sensor, remains challenging due to the difficulty of constructing discriminative geometric features. We present PinNet, a neural network that produces local geometric descriptors from point clouds for place recognition and scanto-scan registration. PinNet incorporates a neural network that generates keypoints and their corresponding descriptors, together with a plane-based geometric self-attention module that models inter-keypoint spatial relationships to enhance descriptor discriminability for loop-closure detection and point-cloud registration. The approach is comprehensively evaluated on multiple datasets collected with different LiDAR sensors. Experimental results demonstrate strong place-recognition performance, precise relative pose estimation, and successful single-shot localization in different environments.

Cite

@article{arxiv.2606.28637,
  title  = {PinNet: Keypoint-Aware Learned Local Descriptors with Geometric Embedding for Loop Closure in LiDAR SLAM},
  author = {Yanlong Ma and Nakul S. Joshi and Christa S. Robison and Philip R. Osteen and Brett T. Lopez},
  journal= {arXiv preprint arXiv:2606.28637},
  year   = {2026}
}