Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2210.05870 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913199694020608 |
|---|---|
| author | Zeng, Ziyin Xu, Yongyang Xie, Zhong Tang, Wei Wan, Jie Wu, Weichao |
| author_facet | Zeng, Ziyin Xu, Yongyang Xie, Zhong Tang, Wei Wan, Jie Wu, Weichao |
| contents | Large-scale point cloud semantic segmentation is an important task in 3D computer vision, which is widely applied in autonomous driving, robotics, and virtual reality. Current large-scale point cloud semantic segmentation methods usually use down-sampling operations to improve computation efficiency and acquire point clouds with multi-resolution. However, this may cause the problem of missing local information. Meanwhile, it is difficult for networks to capture global information in large-scale distributed contexts. To capture local and global information effectively, we propose an end-to-end deep neural network called LACV-Net for large-scale point cloud semantic segmentation. The proposed network contains three main components: 1) a local adaptive feature augmentation module (LAFA) to adaptively learn the similarity of centroids and neighboring points to augment the local context; 2) a comprehensive VLAD module (C-VLAD) that fuses local features with multi-layer, multi-scale, and multi-resolution to represent a comprehensive global description vector; and 3) an aggregation loss function to effectively optimize the segmentation boundaries by constraining the adaptive weight from the LAFA module. Compared to state-of-the-art networks on several large-scale benchmark datasets, including S3DIS, Toronto3D, and SensatUrban, we demonstrated the effectiveness of the proposed network. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_05870 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | LACV-Net: Semantic Segmentation of Large-Scale Point Cloud Scene via Local Adaptive and Comprehensive VLAD Zeng, Ziyin Xu, Yongyang Xie, Zhong Tang, Wei Wan, Jie Wu, Weichao Computer Vision and Pattern Recognition Large-scale point cloud semantic segmentation is an important task in 3D computer vision, which is widely applied in autonomous driving, robotics, and virtual reality. Current large-scale point cloud semantic segmentation methods usually use down-sampling operations to improve computation efficiency and acquire point clouds with multi-resolution. However, this may cause the problem of missing local information. Meanwhile, it is difficult for networks to capture global information in large-scale distributed contexts. To capture local and global information effectively, we propose an end-to-end deep neural network called LACV-Net for large-scale point cloud semantic segmentation. The proposed network contains three main components: 1) a local adaptive feature augmentation module (LAFA) to adaptively learn the similarity of centroids and neighboring points to augment the local context; 2) a comprehensive VLAD module (C-VLAD) that fuses local features with multi-layer, multi-scale, and multi-resolution to represent a comprehensive global description vector; and 3) an aggregation loss function to effectively optimize the segmentation boundaries by constraining the adaptive weight from the LAFA module. Compared to state-of-the-art networks on several large-scale benchmark datasets, including S3DIS, Toronto3D, and SensatUrban, we demonstrated the effectiveness of the proposed network. |
| title | LACV-Net: Semantic Segmentation of Large-Scale Point Cloud Scene via Local Adaptive and Comprehensive VLAD |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2210.05870 |