HOTFLoc++: End-to-End Hierarchical LiDAR Place Recognition, Re-Ranking, and 6-DoF Metric Localisation in Forests
This work addresses the problem of accurate and efficient localization in cluttered, self-similar forest environments for robotics and autonomous systems, representing a strong specific gain with novel method elements.
The paper tackles LiDAR place recognition and localization in forests by proposing HOTFLoc++, an end-to-end framework that uses hierarchical descriptors and multi-scale geometric verification to improve robustness and reduce errors. It achieves an average Recall@1 of 90.7% on CS-Wild-Places, a 29.6 percentage point improvement over baselines, with runtime improvements of two orders of magnitude over RANSAC and under 2 m and 5 degrees error for 97.2% of registration attempts.
This article presents HOTFLoc++, an end-to-end framework for LiDAR place recognition, re-ranking, and 6-DoF metric localisation in forests. Leveraging an octree-based transformer, our approach extracts hierarchical local descriptors 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 a learnable multi-scale geometric verification module to reduce re-ranking failures in the presence of degraded single-scale correspondences. Our coarse-to-fine registration approach achieves comparable or lower localisation errors to baselines, with runtime improvements of two orders of magnitude over RANSAC 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 96.0% on Wild-Places and MulRan, respectively. Our method achieves under 2 m and 5 degrees error for 97.2% of 6-DoF registration attempts, with our multi-scale re-ranking module reducing localisation errors by ~2$\times$ on average. The code will be available upon acceptance.