Figure/Table detail

Semantic Segmentation Method of Street Point Cloud based on Deep-Supervised Multi-Scale Self-Attention
Guangchao LIU, Chenxiao ZHANG, Lei HU
Remote Sensing Technology and Application, 2025, 40(6): 1626-1636.   DOI: 10.11873/j.issn.1004-0323.2025.6.1626

实验模型OAmIoU道路道路标线植被建筑公用线路电线杆汽车围栏
PointNet++91.256.691.47.689.874.068.659.554.07.5
PointNet++ (MSG)90.653.190.70.086.775.856.260.944.510.2
DGCNN89.049.690.60.481.364.047.156.949.37.3
KPFCNN91.760.390.20.086.886.881.173.142.921.6
MS-PCNN91.558.091.03.590.577.362.368.553.617.1
TGNet91.658.391.410.691.076.968.366.354.18.2
MS-TGNet91.761.090.918.892.280.669.471.251.113.6
RandLA-Net96.678.096.666.796.289.385.981.078.829.5
Point Transformer96.879.996.764.695.991.087.679.087.536.9
本文方法97.282.297.165.895.790.886.280.293.648.1
Table 1 Semantic segmentation results of different models on Toronto 3D dataset
Other figure/table from this article