Semantic Segmentation for Point Clouds via Semantic-Based Local Aggregation and Multi-Scale Global Pyramid
Recently, point-based networks have begun to prevail because they retain more original geometric information from point clouds than other deep learning-based methods. However, we observe that: (1) the set abstraction design for local aggregation in point-based networks neglects that the points in a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/11/1/11 |
| _version_ | 1797439520903266304 |
|---|---|
| author | Shipeng Cao Huaici Zhao Pengfei Liu |
| author_facet | Shipeng Cao Huaici Zhao Pengfei Liu |
| author_sort | Shipeng Cao |
| collection | DOAJ |
| description | Recently, point-based networks have begun to prevail because they retain more original geometric information from point clouds than other deep learning-based methods. However, we observe that: (1) the set abstraction design for local aggregation in point-based networks neglects that the points in a local region may belong to different semantic categories, and (2) most works focus on single-scale local features while ignoring the importance of multi-scale global features. To tackle the above issues, we propose two novel strategies named semantic-based local aggregation (SLA) and multi-scale global pyramid (MGP). The key idea of SLA is to augment local features based on the semantic similarity of neighboring points in the local region. Additionally, we propose a hierarchical global aggregation (HGA) module to extend local feature aggregation to global feature aggregation. Based on HGA, we introduce MGP to obtain discriminative multi-scale global features from multi-resolution point cloud scenes. Extensive experiments on two prevailing benchmarks, S3DIS and Semantic3D, demonstrate the effectiveness of our method. |
| first_indexed | 2024-03-09T11:54:10Z |
| format | Article |
| id | doaj.art-1820382fb577454b8debf8521a577542 |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-09T11:54:10Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-1820382fb577454b8debf8521a5775422023-11-30T23:10:40ZengMDPI AGMachines2075-17022022-12-011111110.3390/machines11010011Semantic Segmentation for Point Clouds via Semantic-Based Local Aggregation and Multi-Scale Global PyramidShipeng Cao0Huaici Zhao1Pengfei Liu2Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaShenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaShenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaRecently, point-based networks have begun to prevail because they retain more original geometric information from point clouds than other deep learning-based methods. However, we observe that: (1) the set abstraction design for local aggregation in point-based networks neglects that the points in a local region may belong to different semantic categories, and (2) most works focus on single-scale local features while ignoring the importance of multi-scale global features. To tackle the above issues, we propose two novel strategies named semantic-based local aggregation (SLA) and multi-scale global pyramid (MGP). The key idea of SLA is to augment local features based on the semantic similarity of neighboring points in the local region. Additionally, we propose a hierarchical global aggregation (HGA) module to extend local feature aggregation to global feature aggregation. Based on HGA, we introduce MGP to obtain discriminative multi-scale global features from multi-resolution point cloud scenes. Extensive experiments on two prevailing benchmarks, S3DIS and Semantic3D, demonstrate the effectiveness of our method.https://www.mdpi.com/2075-1702/11/1/11point clouddeep learningsemantic segmentationfeature aggregation |
| spellingShingle | Shipeng Cao Huaici Zhao Pengfei Liu Semantic Segmentation for Point Clouds via Semantic-Based Local Aggregation and Multi-Scale Global Pyramid Machines point cloud deep learning semantic segmentation feature aggregation |
| title | Semantic Segmentation for Point Clouds via Semantic-Based Local Aggregation and Multi-Scale Global Pyramid |
| title_full | Semantic Segmentation for Point Clouds via Semantic-Based Local Aggregation and Multi-Scale Global Pyramid |
| title_fullStr | Semantic Segmentation for Point Clouds via Semantic-Based Local Aggregation and Multi-Scale Global Pyramid |
| title_full_unstemmed | Semantic Segmentation for Point Clouds via Semantic-Based Local Aggregation and Multi-Scale Global Pyramid |
| title_short | Semantic Segmentation for Point Clouds via Semantic-Based Local Aggregation and Multi-Scale Global Pyramid |
| title_sort | semantic segmentation for point clouds via semantic based local aggregation and multi scale global pyramid |
| topic | point cloud deep learning semantic segmentation feature aggregation |
| url | https://www.mdpi.com/2075-1702/11/1/11 |
| work_keys_str_mv | AT shipengcao semanticsegmentationforpointcloudsviasemanticbasedlocalaggregationandmultiscaleglobalpyramid AT huaicizhao semanticsegmentationforpointcloudsviasemanticbasedlocalaggregationandmultiscaleglobalpyramid AT pengfeiliu semanticsegmentationforpointcloudsviasemanticbasedlocalaggregationandmultiscaleglobalpyramid |