SAT-Former: An Efficient 3-D Transformer With Semantic Aggregated Point Tokenizer for Point Cloud Semantic Segmentation in Urban Scenes

3D Transformers have advanced point cloud understanding, but prevalent token generation methods (e.g., Farthest Point Sampling and k-Nearest Neighbors clustering) over-rely on geometric properties while neglecting semantic information. In urban scene point clouds, these methods cannot easily form semantically homogeneous neighborhoods, which forces semantic confusion in point tokens and weakening the self-attention mechanism's ability to model token similarity. Additionally, processing large-scale point clouds leads to excessive tokens, imposing high computational costs of attention calculations and reducing efficiency. Therefore, from the perspective of semantic information, this paper re-examines the point token generation problem and accordingly proposes an efficient 3D Transformer with <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</u>emantic <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</u>ggregated point <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</u>okenizer (SAT-Former) for point cloud semantic segmentation in urban scenes. The developed tokenizer comprises two key modules: the Relation Reasoning Module (RRM) and the Feature Mapping Module (FMM). RRM captures inter-token relationships, generating semantic homogeneity guidance to effectively transmission and integrate semantic information, thereby reducing semantic confusion. FMM maps point-level features onto the semantically homogeneous guided tokens generated by RRM, enhancing token expressiveness while preserving essential details. We evaluate SAT-Former on three urban scene point cloud datasets: Hessigheim 3D (H3D), Toronto-3D (T3D), and SensatUrban, demonstrating competitive performance and up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$30\times$</tex-math></inline-formula> faster inference efficiency than baseline methods while maintaining >95% of their accuracy. Additionally, extensive visualization experiments highlight the semantic homogeneity and feature representativeness of the generated tokens, providing insights into the model's internal mechanisms and validating its effectiveness.