3DLST: 3D Learnable Supertoken Transformer for LiDAR point cloud scene segmentation

3D Transformers have achieved great success in point cloud understanding and representation. However, there is still considerable scope for further development in effective and efficient Transformers for large-scale LiDAR point cloud scene segmentation. This paper proposes a novel 3D Transformer framework, named 3D Learnable Supertoken Transformer (3DLST). The key contributions are summarized as follows. Firstly, we introduce the first Dynamic Supertoken Optimization (DSO) block for efficient token clustering and aggregating, where the learnable supertoken definition avoids the time-consuming pre-processing of traditional superpoint generation. Since the learnable supertokens can be dynamically optimized by multi-level deep features during network learning, they are tailored to the semantic homogeneity-aware token clustering. Secondly, an efficient Cross-Attention-guided Upsampling (CAU) block is proposed for token reconstruction from optimized supertokens. Thirdly, the 3DLST is equipped with a novel W-net architecture instead of the common U-net design, which is more suitable for Transformer-based feature learning. The SOTA performance on challenging LiDAR datasets (airborne MultiSpectral LiDAR (MS-LiDAR) (89.3% of the average $F_1$ score) and DALES (80.2% of mIoU)) demonstrate the superiority of 3DLST. Furthermore, 3DLST also achieves satisfactory results in terms of algorithm efficiency, which is up to 5$\times$ faster than previous best-performing methods.