DNet: Dynamic Neighborhood Feature Learning in Point Cloud
Neighborhood selection is very important for local region feature learning in point cloud learning networks. Different neighborhood selection schemes may lead to quite different results for point cloud processing tasks. The existing point cloud learning networks mainly adopt the approach of customiz...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/7/2327 |
| _version_ | 1797539811542695936 |
|---|---|
| author | Fujing Tian Zhidi Jiang Gangyi Jiang |
| author_facet | Fujing Tian Zhidi Jiang Gangyi Jiang |
| author_sort | Fujing Tian |
| collection | DOAJ |
| description | Neighborhood selection is very important for local region feature learning in point cloud learning networks. Different neighborhood selection schemes may lead to quite different results for point cloud processing tasks. The existing point cloud learning networks mainly adopt the approach of customizing the neighborhood, without considering whether the selected neighborhood is reasonable or not. To solve this problem, this paper proposes a new point cloud learning network, denoted as Dynamic neighborhood Network (DNet), to dynamically select the neighborhood and learn the features of each point. The proposed DNet has a multi-head structure which has two important modules: the Feature Enhancement Layer (FELayer) and the masking mechanism. The FELayer enhances the manifold features of the point cloud, while the masking mechanism is used to remove the neighborhood points with low contribution. The DNet can learn the manifold features and spatial geometric features of point cloud, and obtain the relationship between each point and its effective neighborhood points through the masking mechanism, so that the dynamic neighborhood features of each point can be obtained. Experimental results on three public datasets demonstrate that compared with the state-of-the-art learning networks, the proposed DNet shows better superiority and competitiveness in point cloud processing task. |
| first_indexed | 2024-03-10T12:51:10Z |
| format | Article |
| id | doaj.art-4901195134c54596b50f9fa83affd134 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T12:51:10Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4901195134c54596b50f9fa83affd1342023-11-21T13:01:17ZengMDPI AGSensors1424-82202021-03-01217232710.3390/s21072327DNet: Dynamic Neighborhood Feature Learning in Point CloudFujing Tian0Zhidi Jiang1Gangyi Jiang2Faculty of Information Science and Engineering, Ningbo University, Ningbo 315211, ChinaFaculty of Information Science and Engineering, Ningbo University, Ningbo 315211, ChinaFaculty of Information Science and Engineering, Ningbo University, Ningbo 315211, ChinaNeighborhood selection is very important for local region feature learning in point cloud learning networks. Different neighborhood selection schemes may lead to quite different results for point cloud processing tasks. The existing point cloud learning networks mainly adopt the approach of customizing the neighborhood, without considering whether the selected neighborhood is reasonable or not. To solve this problem, this paper proposes a new point cloud learning network, denoted as Dynamic neighborhood Network (DNet), to dynamically select the neighborhood and learn the features of each point. The proposed DNet has a multi-head structure which has two important modules: the Feature Enhancement Layer (FELayer) and the masking mechanism. The FELayer enhances the manifold features of the point cloud, while the masking mechanism is used to remove the neighborhood points with low contribution. The DNet can learn the manifold features and spatial geometric features of point cloud, and obtain the relationship between each point and its effective neighborhood points through the masking mechanism, so that the dynamic neighborhood features of each point can be obtained. Experimental results on three public datasets demonstrate that compared with the state-of-the-art learning networks, the proposed DNet shows better superiority and competitiveness in point cloud processing task.https://www.mdpi.com/1424-8220/21/7/2327point clouddynamic neighborhoodfeature learningattention mechanismmasking mechanism |
| spellingShingle | Fujing Tian Zhidi Jiang Gangyi Jiang DNet: Dynamic Neighborhood Feature Learning in Point Cloud Sensors point cloud dynamic neighborhood feature learning attention mechanism masking mechanism |
| title | DNet: Dynamic Neighborhood Feature Learning in Point Cloud |
| title_full | DNet: Dynamic Neighborhood Feature Learning in Point Cloud |
| title_fullStr | DNet: Dynamic Neighborhood Feature Learning in Point Cloud |
| title_full_unstemmed | DNet: Dynamic Neighborhood Feature Learning in Point Cloud |
| title_short | DNet: Dynamic Neighborhood Feature Learning in Point Cloud |
| title_sort | dnet dynamic neighborhood feature learning in point cloud |
| topic | point cloud dynamic neighborhood feature learning attention mechanism masking mechanism |
| url | https://www.mdpi.com/1424-8220/21/7/2327 |
| work_keys_str_mv | AT fujingtian dnetdynamicneighborhoodfeaturelearninginpointcloud AT zhidijiang dnetdynamicneighborhoodfeaturelearninginpointcloud AT gangyijiang dnetdynamicneighborhoodfeaturelearninginpointcloud |