.png){kind=icon}
返回
Associative graph convolution network for point cloud analysis
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.111152.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Since point cloud is the raw output of most 3D sensors, its effective analysis is in huge demand in the field of autonomous driving and robotic manipulation. However, directly processing point clouds is challenging because point clouds area kind of disordered and unstructured geometric data. Recently, numerous graph convolution neural networks are proposed for introducing graph structure to point clouds yet far from perfect. Specially, DGCNN tries to learn local geometric of points in semantic space and recomputes the graph using nearest neighbors in the feature space in each layer. However, it discards all the information of the previous graph after each graph update, which neglects the relations between each dynamic update. To this end, we propose an associative graph convolution neural network (AGCN) which mainly consists of associative graph convolution (AGConv) and two kinds of residual connections. AGConv additionally considers the information from the previous graph when computing the edge function on current local neighborhoods in each layer, and it can precisely and continuously capture the local geometric features on point clouds. Residual connections further explore the semantic relations between layers for effective learning on point clouds. Extensive experiments on several benchmark datasets show that our network achieves competitive classification and segmentation results.
Keyword:
Point cloud analysis
GCN
Classification
Segmentation
期刊
IF:
7.6
论文数:
1.4W
被引数:
4.5W
机构
引用论文
Continuous conditional random field convolution for point cloud segmentation.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏A novel GCN-based point cloud classification model robust to pose variances一种新的基于GCN的位姿方差鲁棒性点云分类模型PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容