SPPSFormer: High-quality Superpoint-based Transformer for Roof Plane Instance Segmentation from Point Clouds

TL;DR

This paper introduces SPPSFormer, a novel transformer-based method for roof plane segmentation from point clouds, utilizing high-quality superpoints, handcrafted features, and a specialized decoder to achieve state-of-the-art results with reduced annotation effort.

Contribution

The paper proposes a two-stage superpoint generation process for high-quality superpoints, integrates handcrafted features, and designs a combined Kolmogorov-Arnold Network and Transformer decoder for improved roof plane segmentation.

Findings

Achieves state-of-the-art performance on multiple datasets.

Model is robust to boundary annotation variations.

Identifies key factors affecting segmentation performance.

Abstract

Transformers have been seldom employed in point cloud roof plane instance segmentation, which is the focus of this study, and existing superpoint Transformers suffer from limited performance due to the use of low-quality superpoints. To address this challenge, we establish two criteria that high-quality superpoints for Transformers should satisfy and introduce a corresponding two-stage superpoint generation process. The superpoints generated by our method not only have accurate boundaries, but also exhibit consistent geometric sizes and shapes, both of which greatly benefit the feature learning of superpoint Transformers. To compensate for the limitations of deep learning features when the training set size is limited, we incorporate multidimensional handcrafted features into the model. Additionally, we design a decoder that combines a Kolmogorov-Arnold Network with a Transformer module to improve instance prediction and mask extraction. Finally, our network's predictions are refined using traditional algorithm-based postprocessing. For evaluation, we annotated a real-world dataset and corrected annotation errors in the existing RoofN3D dataset. Experimental results show that our method achieves state-of-the-art performance on our dataset, as well as both the original and reannotated RoofN3D datasets. Moreover, our model is not sensitive to plane boundary annotations during training, significantly reducing the annotation burden. Through comprehensive experiments, we also identified key factors influencing roof plane segmentation performance: in addition to roof types, variations in point cloud density, density uniformity, and 3D point precision have a considerable impact. These findings underscore the importance of incorporating data augmentation strategies that account for point cloud quality to enhance model robustness under diverse and challenging conditions.