In this work, we target the problem of uncertain points refinement for image-based LiDAR point cloud semantic segmentation (LiDAR PCSS). This problem mainly results from the boundary-blurring problem of convolution neural networks (CNNs) and quantitation loss of spherical projection, which are often hard to avoid for common image-based LiDAR PCSS approaches. We propose a plug-and-play transformer-based uncertain point refiner (TransUPR) to address the problem. Through local feature aggregation, uncertain point localization, and self-attention-based transformer design, TransUPR, integrated into an existing range image-based LiDAR PCSS approach (e.g., CENet), achieves the state-of-the-art performance (68.2% mIoU) on Semantic-KITTI benchmark, which provides a performance improvement of 0.6% on the mIoU.

翻译：本文针对基于图像的激光雷达点云语义分割（LiDAR PCSS）中的不确定点精化问题展开研究。该问题主要源于卷积神经网络（CNN）的边界模糊效应以及球面投影带来的量化损失，这是常规基于图像的LiDAR PCSS方法难以规避的固有缺陷。我们提出一种即插即用的基于Transformer的不确定点精化器（TransUPR）来解决该问题。通过局部特征聚合、不确定点定位以及基于自注意力机制的Transformer设计，TransUPR在集成至现有距离图像型LiDAR PCSS方法（如CENet）后，在Semantic-KITTI基准上达到当前最优性能（68.2% mIoU），相较于原始方法在平均交并比指标上提升0.6%。