SK-TreePCN: Skeleton-Embedded Transformer Model for Point Cloud Completion of Individual Trees from Simulated to Real Data
Tree structural information is essential for studying forest ecosystem functions, driving mechanisms, and global change response mechanisms. Although current terrestrial laser scanning (TLS) can acquire high-precision 3D structural information of forests, mutual occlusion between trees, the scanner’...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/4/656 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849718712370724864 |
|---|---|
| author | Haifeng Xu Yongjian Huai Xun Zhao Qingkuo Meng Xiaoying Nie Bowen Li Hao Lu |
| author_facet | Haifeng Xu Yongjian Huai Xun Zhao Qingkuo Meng Xiaoying Nie Bowen Li Hao Lu |
| author_sort | Haifeng Xu |
| collection | DOAJ |
| description | Tree structural information is essential for studying forest ecosystem functions, driving mechanisms, and global change response mechanisms. Although current terrestrial laser scanning (TLS) can acquire high-precision 3D structural information of forests, mutual occlusion between trees, the scanner’s field of view, and terrain changes make the point clouds captured by laser scanning sensors incomplete, further hindering downstream tasks. This study proposes a skeleton-embedded tree point cloud completion method, termed SK-TreePCN, which recovers complete individual tree point clouds from incomplete scanning data in the field. SK-TreePCN employs a transformer trained on simulated point clouds generated by a 3D radiative transfer model. Unlike existing point cloud completion algorithms designed for regular shapes and simple structures, the SK-TreePCN method addresses structurally heterogeneous trees. The 3D radiative transfer model LESS, which can simulate various TLS data over highly heterogeneous scenes, is employed to generate massive point clouds with training labels. Among the various point cloud completion methods evaluated, SK-TreePCN exhibits outstanding performance regarding the Chamfer distance (CD) and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>F</mi><mn>1</mn></mrow></semantics></math></inline-formula> Score. The generated point clouds display a more natural appearance and clearer branches. The accuracy of tree height and diameter at breast height extracted from the recovered point cloud achieved <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi mathvariant="bold-italic">R</mi><mn>2</mn></msup></mrow></semantics></math></inline-formula> values of 0.929 and 0.904, respectively. SK-TreePCN demonstrates applicability and robustness in recovering individual tree point clouds. It demonstrated great potential for TLS-based field measurements of trees, refining point cloud 3D reconstruction and tree information extraction and reducing field data collection labor while retaining satisfactory data quality. |
| format | Article |
| id | doaj-art-4144f97c7bd54ea291b3ab9f0a7786a0 |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-4144f97c7bd54ea291b3ab9f0a7786a02025-08-20T03:12:19ZengMDPI AGRemote Sensing2072-42922025-02-0117465610.3390/rs17040656SK-TreePCN: Skeleton-Embedded Transformer Model for Point Cloud Completion of Individual Trees from Simulated to Real DataHaifeng Xu0Yongjian Huai1Xun Zhao2Qingkuo Meng3Xiaoying Nie4Bowen Li5Hao Lu6School of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaState Forestry and Grassland Administration Key Laboratory of Forest Resources and Environmental Management, Beijing Forestry University, Beijing 100083, ChinaSchool of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaResearch Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, ChinaSchool of Information Science and Technology, Beijing Forestry University, Beijing 100083, ChinaTree structural information is essential for studying forest ecosystem functions, driving mechanisms, and global change response mechanisms. Although current terrestrial laser scanning (TLS) can acquire high-precision 3D structural information of forests, mutual occlusion between trees, the scanner’s field of view, and terrain changes make the point clouds captured by laser scanning sensors incomplete, further hindering downstream tasks. This study proposes a skeleton-embedded tree point cloud completion method, termed SK-TreePCN, which recovers complete individual tree point clouds from incomplete scanning data in the field. SK-TreePCN employs a transformer trained on simulated point clouds generated by a 3D radiative transfer model. Unlike existing point cloud completion algorithms designed for regular shapes and simple structures, the SK-TreePCN method addresses structurally heterogeneous trees. The 3D radiative transfer model LESS, which can simulate various TLS data over highly heterogeneous scenes, is employed to generate massive point clouds with training labels. Among the various point cloud completion methods evaluated, SK-TreePCN exhibits outstanding performance regarding the Chamfer distance (CD) and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>F</mi><mn>1</mn></mrow></semantics></math></inline-formula> Score. The generated point clouds display a more natural appearance and clearer branches. The accuracy of tree height and diameter at breast height extracted from the recovered point cloud achieved <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msup><mi mathvariant="bold-italic">R</mi><mn>2</mn></msup></mrow></semantics></math></inline-formula> values of 0.929 and 0.904, respectively. SK-TreePCN demonstrates applicability and robustness in recovering individual tree point clouds. It demonstrated great potential for TLS-based field measurements of trees, refining point cloud 3D reconstruction and tree information extraction and reducing field data collection labor while retaining satisfactory data quality.https://www.mdpi.com/2072-4292/17/4/656point cloud completionindividual treetree skeletonterrestrial laser scanningsimulation |
| spellingShingle | Haifeng Xu Yongjian Huai Xun Zhao Qingkuo Meng Xiaoying Nie Bowen Li Hao Lu SK-TreePCN: Skeleton-Embedded Transformer Model for Point Cloud Completion of Individual Trees from Simulated to Real Data Remote Sensing point cloud completion individual tree tree skeleton terrestrial laser scanning simulation |
| title | SK-TreePCN: Skeleton-Embedded Transformer Model for Point Cloud Completion of Individual Trees from Simulated to Real Data |
| title_full | SK-TreePCN: Skeleton-Embedded Transformer Model for Point Cloud Completion of Individual Trees from Simulated to Real Data |
| title_fullStr | SK-TreePCN: Skeleton-Embedded Transformer Model for Point Cloud Completion of Individual Trees from Simulated to Real Data |
| title_full_unstemmed | SK-TreePCN: Skeleton-Embedded Transformer Model for Point Cloud Completion of Individual Trees from Simulated to Real Data |
| title_short | SK-TreePCN: Skeleton-Embedded Transformer Model for Point Cloud Completion of Individual Trees from Simulated to Real Data |
| title_sort | sk treepcn skeleton embedded transformer model for point cloud completion of individual trees from simulated to real data |
| topic | point cloud completion individual tree tree skeleton terrestrial laser scanning simulation |
| url | https://www.mdpi.com/2072-4292/17/4/656 |
| work_keys_str_mv | AT haifengxu sktreepcnskeletonembeddedtransformermodelforpointcloudcompletionofindividualtreesfromsimulatedtorealdata AT yongjianhuai sktreepcnskeletonembeddedtransformermodelforpointcloudcompletionofindividualtreesfromsimulatedtorealdata AT xunzhao sktreepcnskeletonembeddedtransformermodelforpointcloudcompletionofindividualtreesfromsimulatedtorealdata AT qingkuomeng sktreepcnskeletonembeddedtransformermodelforpointcloudcompletionofindividualtreesfromsimulatedtorealdata AT xiaoyingnie sktreepcnskeletonembeddedtransformermodelforpointcloudcompletionofindividualtreesfromsimulatedtorealdata AT bowenli sktreepcnskeletonembeddedtransformermodelforpointcloudcompletionofindividualtreesfromsimulatedtorealdata AT haolu sktreepcnskeletonembeddedtransformermodelforpointcloudcompletionofindividualtreesfromsimulatedtorealdata |