Point Cloud Segmentation Using Sparse Temporal Local Attention

2021-12-01 · Joshua Knights, Peyman Moghadam, Clinton Fookes, Sridha Sridharan

Point clouds are a key modality used for perception in autonomous vehicles, providing the means for a robust geometric understanding of the surrounding environment. However despite the sensor outputs from autonomous vehicles being naturally temporal in nature, there is still limited exploration of exploiting point cloud sequences for 3D seman-tic segmentation. In this paper we propose a novel Sparse Temporal Local Attention (STELA) module which aggregates intermediate features from a local neighbourhood in previous point cloud frames to provide a rich temporal context to the decoder. Using the sparse local neighbourhood enables our approach to gather features more flexibly than those which directly match point features, and more efficiently than those which perform expensive global attention over the whole point cloud frame. We achieve a competitive mIoU of 64.3% on the SemanticKitti dataset, and demonstrate significant improvement over the single-frame baseline in our ablation studies.

📄 PDF Abstract BibTeX arXiv:2112.00289

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Vehicles Decoder Point Cloud Segmentation

SpSequenceNet: Semantic Segmentation Network on 4D Point Clouds

2020-06-01 · CVPR 2020 6 · Hanyu Shi, Guosheng Lin, Hao Wang, Tzu-Yi Hung 외

Point clouds are useful in many applications like autonomous driving and robotics as they provide natural 3D information of the surrounding environments. While there are extensive research on 3D point clouds, scene under…

Autonomous Driving Scene Understanding Semantic Segmentation

LatticeNet: Fast Spatio-Temporal Point Cloud Segmentation Using Permutohedral Lattices

2021-08-09 · Radu Alexandru Rosu, Peer Schütt, Jan Quenzel, Sven Behnke

Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images. Applying the same methods on 3D data still poses challenges due to the heavy memory requirements…

3D Semantic Segmentation Point Cloud Segmentation Segmentation Semantic Segmentation

DRINet++: Efficient Voxel-as-point Point Cloud Segmentation

2021-11-16 · Maosheng Ye, Rui Wan, Shuangjie Xu, Tongyi Cao 외

Recently, many approaches have been proposed through single or multiple representations to improve the performance of point cloud semantic segmentation. However, these works do not maintain a good balance among performan…

Point Cloud Segmentation Segmentation Semantic Segmentation

Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes

2022-08-13 · Yongqiang Mao, Zonghao Guo, Xiaonan Lu, Zhiqiang Yuan 외

Few-shot segmentation of point cloud remains a challenging task, as there is no effective way to convert local point cloud information to global representation, which hinders the generalization ability of point features.…

Few-Shot Semantic Segmentation Metric Learning Segmentation Semantic Segmentation

ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation

2020-08-12 · Hanwen Cao, Yongyi Lu, Cewu Lu, Bo Pang 외

Recent works of point clouds show that mulit-frame spatio-temporal modeling outperforms single-frame versions by utilizing cross-frame information. In this paper, we further improve spatio-temporal point cloud feature le…

Segmentation