Dijous 11 de juny, el Dipòsit Digital no estarà operatiu de 15:00 a 17:00 h per tasques de manteniment. Disculpeu les molèsties.
El jueves 11 de Junio, el Dipòsit Digital no estará operativo de 15:00 a 17:00 h debido a tareas de mantenimiento. Disculpen las molestias.
Thursday, Jun 11th, the Digital Repository will be unavailable due to a system update.

Document type

Article

Version

Published version

Publication date

Publication license

cc-by-nc-nd (c) Mariona Carós, et al., 2026
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/227057

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

Journal Title

Director/Tutor

Journal ISSN

Volume Title

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.

Citation

Citation

CARÓS, Mariona, et al. Enhancing point cloud semantic segmentation via scalable domain adaptation with LoRA-enabled PointNet++. ISPRS Journal of Photogrammetry and Remote Sensing. 2026. Vol. 19. ISSN 0924-2716. [consulted: 11 of June of 2026]. Available at: https://hdl.handle.net/2445/227057

Export metadata

JSON - METS

Share record