Semantic Segmentation is a crucial component in the perception systems of many applications, such as robotics and autonomous driving that rely on accurate environmental perception and understanding. In literature, several approaches are introduced to attempt LiDAR semantic segmentation task, such as projection-based (range-view or birds-eye-view), and voxel-based approaches. However, they either abandon the valuable 3D topology and geometric relations and suffer from information loss introduced in the projection process or are inefficient. Therefore, there is a need for accurate models capable of processing the 3D driving-scene point cloud in 3D space. In this paper, we propose S3Net, a novel convolutional neural network for LiDAR point cloud semantic segmentation. It adopts an encoder-decoder backbone that consists of Sparse Intra-channel Attention Module (SIntraAM), and Sparse Inter-channel Attention Module (SInterAM) to emphasize the fine details of both within each feature map and among nearby feature maps. To extract the global contexts in deeper layers, we introduce Sparse Residual Tower based upon sparse convolution that suits varying sparsity of LiDAR point cloud. In addition, geo-aware anisotrophic loss is leveraged to emphasize the semantic boundaries and penalize the noise within each predicted regions, leading to a robust prediction. Our experimental results show that the proposed method leads to a large improvement (12\%) compared to its baseline counterpart (MinkNet42 \cite{choy20194d}) on SemanticKITTI \cite{DBLP:conf/iccv/BehleyGMQBSG19} test set and achieves state-of-the-art mIoU accuracy of semantic segmentation approaches.
翻译:语系分解是许多应用的感知系统中一个至关重要的组成部分,例如机器人和自主驱动,这些应用依赖于准确的环境感知和理解。在文献中,采用了几种方法尝试LiDAR语系分解任务,例如基于投影的(测距或鸟眼视)和基于 voxel 的方法。然而,它们要么放弃宝贵的 3D 地形和几何关系,在投影过程中引入信息损失,要么是低效的。因此,需要精确模型,以便能够处理3D驱动点云在 3D 空间的3D驱动点和自主驱动点云。在本文中,我们提出S3Net,S3Net,这是一个新的关于利DAR点云层云层云层云层的神经神经神经网络。它采用了一个摄像机分解骨干骨干骨干骨干骨干骨干骨干骨干,而Speak-Cal-Sendrational-Seqoral-deal-laisa, 一种基于稀释的Cal-deal-deal-deal-deal-deal-deal-deal-deal-deal-deal-laisl strisl strisl maisl maism) 、一个我们的直系、直系、直系、直系、直系、直系、直系、直系、直系、直系、直系、直根根根根根根根根根根根根根根根根根根根根、直至根根、根根根根根、直路、直至根、直至根、直至根、直至根、直至根根根根根根根根根、直至根根、直至根、直至根根、直至根根根根根根根根根根、根根根根根根根根根根根根根根根、直至根、直至根根根根根根根、直至根、直至根、直至根、直至根根根根根、根根根根根根根根根根根根根根根根根根根根根根根根根根根根根根根根根根根根根根根根根根、根根根根、根、根根根根