HOTFLoc++: End-to-End Hierarchical LiDAR Place Recognition, Re-Ranking, and 6-DoF Metric Localisation in Forests

TL;DR

HOTFLoc++ introduces a hierarchical LiDAR place recognition and localisation framework using octree transformers, significantly improving robustness and efficiency in forest and urban environments.

Contribution

It presents a novel multi-scale geometric verification and joint training approach for enhanced place recognition and localisation accuracy.

Findings

Achieves 90.7% Recall@1 on CS-Wild-Places, outperforming baselines.

Reduces localisation errors by approximately 2x with multi-scale re-ranking.

Runs nearly 100 times faster than RANSAC-based registration methods.

Abstract

This article presents HOTFLoc++, an end-to-end hierarchical framework for LiDAR place recognition, re-ranking, and 6-DoF metric localisation in forests. Leveraging an octree-based transformer, our approach extracts features at multiple granularities to increase robustness to clutter, self-similarity, and viewpoint changes in challenging scenarios, including ground-to-ground and ground-to-aerial in forest and urban environments. We propose learnable multi-scale geometric verification to reduce re-ranking failures due to degraded single-scale correspondences. Our joint training protocol enforces multi-scale geometric consistency of the octree hierarchy via joint optimisation of place recognition with re-ranking and localisation, improving place recognition convergence. Our system achieves comparable or lower localisation errors to baselines, with runtime improvements of almost two orders of magnitude over RANSAC-based registration for dense point clouds. Experimental results on public datasets show the superiority of our approach compared to state-of-the-art methods, achieving an average Recall@1 of 90.7% on CS-Wild-Places: an improvement of 29.6 percentage points over baselines, while maintaining high performance on single-source benchmarks with an average Recall@1 of 91.7% and 97.9% on Wild-Places and MulRan, respectively. Our method achieves under 2m and 5$^{\circ}$ error for 97.2% of 6-DoF registration attempts, with our multi-scale re-ranking module reducing localisation errors by ~2x on average. The code is available at https://github.com/csiro-robotics/HOTFLoc.