QC-SF: Improving Computer Vision for Airborne LiDAR Point Clouds of Boreal Forests with Quebec Simulated Forest Dataset

Boreal forest ecosystems are under immense pressure, and while airborne LiDAR has emerged as a powerful monitoring tool, leveraging its large data volumes requires automated analysis. Deep learning methods offer a solution but are hindered by the scarcity of large-scale, labeled datasets in forestry, contrasting to the data-rich urban environments. To address this gap, we introduce the Quebec Simulated Forest (QC-SF), a large-scale, synthetic airborne LiDAR dataset fully labeled for semantic segmentation. QC-SF contains 60,000 forest plots, each composed of a controlled mixture of two dominant species in Quebec's boreal forest: Black Spruce and Balsam Fir. Using this benchmark, we evaluate the performance of five renowned and state-of-the-art point cloud networks: KPConv, MinkUNet, DGCNN, Point Mamba and Point Transformer V3. Our results identify Point Transformer V3 as the most effective architecture, achieving 91.66% mIoU. Furthermore, we validate the sim-to-real transferability of our dataset, demonstrating that augmenting a small number of real-world scans with our synthetic data improves segmentation performance by 6% in mIoU score. QC-SF is available at : qc-sf.org.