Multilateral Cascading Network for Semantic Segmentation of Large-Scale Outdoor Point Clouds
This work addresses the challenge of environment perception and scene understanding for outdoor applications, representing an incremental advance with specific performance gains.
The paper tackled semantic segmentation of large-scale outdoor point clouds by proposing the Multilateral Cascading Network (MCNet), which achieved a 2.1% improvement in overall mIoU on the SensatUrban dataset and a 15.9% gain for small-sample categories.
Semantic segmentation of large-scale outdoor point clouds is of significant importance in environment perception and scene understanding. However, this task continues to present a significant research challenge, due to the inherent complexity of outdoor objects and their diverse distributions in real-world environments. In this study, we propose the Multilateral Cascading Network (MCNet) designed to address this challenge. The model comprises two key components: a Multilateral Cascading Attention Enhancement (MCAE) module, which facilitates the learning of complex local features through multilateral cascading operations; and a Point Cross Stage Partial (P-CSP) module, which fuses global and local features, thereby optimizing the integration of valuable feature information across multiple scales. Our proposed method demonstrates superior performance relative to state-of-the-art approaches across two widely recognized benchmark datasets: Toronto3D and SensatUrban. Especially on the city-scale SensatUrban dataset, our results surpassed the current best result by 2.1\% in overall mIoU and yielded an improvement of 15.9\% on average for small-sample object categories comprising less than 2\% of the total samples, in comparison to the baseline method.