Q Hu, B Yang, L Xie, S Rosa, Y Guo… - … on Pattern Analysis …, 2021 - ieeexplore.ieee.org
… small-scalepointclouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per- point semantics for large-scalepointclouds. The …
Y Chen, Y Xiong, B Zhang, J Zhou, Q Zhang - Computers and Electronics in …, 2021 - Elsevier
… problem of 3D pointcloud semantic segmentation for large-scale … structure of RandLA-Net, a deeper 3D pointcloud semantic … Based on the RandLA-Net algorithm, we replaced random …
L Wang, J Wu, X Liu, X Ma, J Cheng - Complex & Intelligent Systems, 2022 - Springer
… To further demonstrate the advantages of our method compared with RandLA-Net, more results have been given in Table 2. In this table, we have listed the mIOU of segmentation …
… largescale urban pointclouds and an outlook on future directions for 3D pointcloud segmentation at massivescale … baselines PointNet [37] and RandLA-Net [23], we evaluate how the …
X Geng, S Ji, M Lu, L Zhao - Remote Sensing, 2021 - mdpi.com
… for pointcloud segmentation, namely, RandLA-Net, an … and decoder features of the same scales. Second, a channel attentive … of RandLA-Net [23], which sampled the whole pointcloud …
J Zhang, H Chen, B Wang, G Fang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
… In Table 4, we use a similar metric to the RandLA-Net to evaluate the performance of our method and the mainstream methods. Compared to the RandLA-Net, our FARnet requires …
Y Zhao, X Ma, B Hu, Q Zhang, M Ye, G Zhou - Computers & Graphics, 2023 - Elsevier
… 2, we propose a novel method named LG-Net for large-scalepointcloud semantic segmentation. … Compared with RandLA-Net and GA-Net, our method improves OA by 1.0% and 0.5%, …
Y Zhang, Z Li, Y Xie, Y Qu, C Li, T Mei - Proceedings of the AAAI …, 2021 - ojs.aaai.org
… Moreover, we implement RandLA-Net on the selfsupervised task by modifying the final output layer. That is, the output of the network is a 6-dimension vector which contains the …
Y Shao, G Tong, H Peng - Neurocomputing, 2022 - Elsevier
… Net thanks to these two modules and evaluate LGS-Net on three public large-scalepoint clouds … Compared with RandLA-Net, we design the LGSR module to represent z-axis rotation-…