Impact of color and mixing proportion of synthetic point clouds on semantic segmentation
It addresses a data shortage problem for built environment understanding by providing insights into optimizing synthetic point clouds for training segmentation models, though it is incremental in nature.
This paper investigated how synthetic point clouds (SPC) with different colors and mixing proportions affect deep learning-based semantic segmentation, finding that SPC with real colors outperforms uniform colors by over 8.2% in accuracy and that a mixing proportion above 70% generally yields better performance.
Deep learning (DL)-based point cloud segmentation is essential for understanding built environment. Despite synthetic point clouds (SPC) having the potential to compensate for data shortage, how synthetic color and mixing proportion impact DL-based segmentation remains a long-standing question. Therefore, this paper addresses this question with extensive experiments by introducing: 1) method to generate SPC with real colors and uniform colors from BIM, and 2) enhanced benchmarks for better performance evaluation. Experiments on DL models including PointNet, PointNet++, and DGCNN show that model performance on SPC with real colors outperforms that on SPC with uniform colors by 8.2 % + on both OA and mIoU. Furthermore, a higher than 70 % mixing proportion of SPC usually leads to better performance. And SPC can replace real ones to train a DL model for detecting large and flat building elements. Overall, this paper unveils the performance-improving mechanism of SPC and brings new insights to boost SPC's value (for building large models for point clouds).