Unsupervised Class-Guided Synthetic-to-Real Domain Adaptation for Plot-Level Forest UAV LiDAR Semantic Segmentation

Semantic segmentation of forest point clouds is pivotal for automated forest inventory but is severely constrained by the scarcity of high-quality real-world annotations. Although synthetic forest point clouds provide a scalable alternative for training, models trained on synthetic data often suffer from pronounced performance degradation when transferred to real forest scenes, due to domain shifts coupled with extreme structural heterogeneity and long-tailed semantic distributions. To address these challenges, we propose ForestPlotUDA, an unsupervised domain adaptation framework specifically designed for plot-level forest UAV LiDAR semantic segmentation. Unlike generic adaptation methods that rely on global feature alignment or dense pseudo-labeling, ForestPlotUDA explicitly targets the severe class imbalance and plot-wise structural variability inherent in forest environments, where ecologically critical woody components are sparsely distributed and easily overwhelmed by dominant foliage points. The proposed framework integrates decoupled feature normalization and class-guided self-training, enabling stable cross-domain adaptation under highly imbalanced and sparse supervision. Experimental results on the FOR-instance benchmark demonstrate that ForestPlotUDA improves the mean Intersection-over-Union from 54.71% to 61.50%. Notably, using only five pseudo-labeled points per class, the IoU of the challenging wood class increases from 22.82% to 40.90%, highlighting the effectiveness of the proposed approach for annotation-free forest UAV LiDAR analysis. Additional experiments on SegmentedForests further demonstrate that ForestPlotUDA consistently improves over direct synthetic-to-real transfer on ground-based TLS/MLS forest point clouds. These results indicate that explicitly accounting for structural heterogeneity and class imbalance is critical for synthetic-to-real adaptation in forest point clouds, paving the way for fully automated and low-cost forest inventory systems across diverse forest ecosystems.