Enhancing point cloud semantic segmentation via scalable domain adaptation with LoRA-enabled PointNet++

Abstract

Semantic segmentation of airborne LiDAR point clouds enables a broad range of urban and environmental applications. However, domain shifts between training and operational data, as well asthefrequentemergenceofnewsemanticclasses,posesignificantchallengesfordeploying deep learning models effectively. In this work, we explore the integration of Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning technique, into the PointNet++ architecture to address these challenges. We evaluate LoRA in two realistic scenarios: domain adaptation and incremental learning with novel classes, using subsets of large-scale LiDAR datasets under constrained labeled data settings. Our experiments show that LoRA outperforms traditional full f ine-tuning, achieving notable gains (+3.1 IoU for specific classes and +0.3 mIoUonTerLiDAR, +2.7 mIoU on DALES), while exhibiting greater resistance to catastrophic forgetting and improved generalization, particularly for underrepresented classes. Furthermore, LoRA exceeds baseline accuracy with substantially fewer trainable parameters (73.4% reduction), highlighting its suitability for resource-constrained deployment scenarios. We also present TerLiDAR, a publicly available annotated airborne LiDAR dataset covering 51.4 km2 along the Ter River in Catalonia, Spain. It contributes to increasing the diversity of semantic segmentation benchmarks and advancing 3D scene understanding in remote sensing.