InLiER: Learning-Free Heterogeneous LiDAR Place Recognition via Intermediate Mixed-Radix Structural Keypoint Tokenization
Computer Vision and Pattern RecognitionRobotics
Summary
The authors developed InLiER, a method to help robots recognize places using LiDAR sensors even when these sensors have different views or scanning styles. Instead of relying on learning-based models, their approach uses a clever way to turn 3D features into compact tokens that capture height, shape, and direction. They then use these tokens in steps to quickly find and confirm matches between places, helping with accurate pose estimation. Their method works well on a benchmark dataset and real tests, often outperforming other methods, especially when different LiDAR sensors are involved.
Authors
Nikolaos Stathoulopoulos, George Nikolakopoulos
Abstract
LiDAR place recognition supports loop closure, relocalization, and multi-agent map management. As robotic platforms increasingly combine LiDARs with different fields of view, resolutions, and scanning patterns, existing descriptors degrade because they are tightly coupled to sensor-specific characteristics. We present InLiER, a learning-free pipeline based on an intermediate tokenization step. Height-sliced keypoints from structural elements receive mixed-radix token IDs encoding height, radial distance, local shape, and azimuth from local 3D geometry, in a compact sub-2KB representation. The same vocabulary is reorganized across three retrieval stages: height-ceiling histogram intersection for fast rotation-invariant shortlisting, binary bitmask alignment for yaw estimation and reranking, and token-guided geometric verification for 6-DoF pose estimation. InLiER achieves state-of-the-art performance on the HeLiPR dataset and in real-world field experiments, among modern handcrafted methods and outperforms the learning-based baseline on most cross-sensor configurations.