That's My Point: Compact Object-centric LiDAR Pose Estimation for Large-scale Outdoor Localisation
This addresses the problem of scalable outdoor localization for autonomous systems by reducing storage requirements, though it is incremental as it builds on existing object-centric and registration approaches.
The paper tackles 3D pose estimation for LiDAR scans with minimal storage by clustering points into semantic objects represented as centroids and classes, enabling scalable mapping and localization. It achieves accurate metric estimates comparable to state-of-the-art methods with an average representation size of 1.33 kB, about half the size.
This paper is about 3D pose estimation on LiDAR scans with extremely minimal storage requirements to enable scalable mapping and localisation. We achieve this by clustering all points of segmented scans into semantic objects and representing them only with their respective centroid and semantic class. In this way, each LiDAR scan is reduced to a compact collection of four-number vectors. This abstracts away important structural information from the scenes, which is crucial for traditional registration approaches. To mitigate this, we introduce an object-matching network based on self- and cross-correlation that captures geometric and semantic relationships between entities. The respective matches allow us to recover the relative transformation between scans through weighted Singular Value Decomposition (SVD) and RANdom SAmple Consensus (RANSAC). We demonstrate that such representation is sufficient for metric localisation by registering point clouds taken under different viewpoints on the KITTI dataset, and at different periods of time localising between KITTI and KITTI-360. We achieve accurate metric estimates comparable with state-of-the-art methods with almost half the representation size, specifically 1.33 kB on average.