Rotation-Invariant Convolution With Point Sort and Curvature Radius for Point Cloud Classification and Segmentation
Recently, the distance-based and angle-based geometric descriptors and local reference axes have been used widely to explore the rotation invariance of point clouds. However, they tend to encounter with two challenges. (i) Similar distances and angles among different points would lead to ambiguous d...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10838555/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592965408653312 |
|---|---|
| author | Zhao Shen Xin Jia Jinglei Zhang |
| author_facet | Zhao Shen Xin Jia Jinglei Zhang |
| author_sort | Zhao Shen |
| collection | DOAJ |
| description | Recently, the distance-based and angle-based geometric descriptors and local reference axes have been used widely to explore the rotation invariance of point clouds. However, they tend to encounter with two challenges. (i) Similar distances and angles among different points would lead to ambiguous descriptions of local regions. (ii) Establishing a local reference axis may reduce the number of neighbor points, resulting in information loss in local regions. To this end, a Rotation-invariant Convolution with Point Sorting and Curvature Radius <inline-formula> <tex-math notation="LaTeX">$\text {(RCPC)}$ </tex-math></inline-formula> is proposed. Firstly, to solve the challenge (i), a neighbor point sorting module <inline-formula> <tex-math notation="LaTeX">$\text {(NPS)}$ </tex-math></inline-formula> is introduced. Neighbor points on the local tangent disk are sorted according to the local reference axis at the first step. When neighbor points occlude each other along the local reference axis direction, NPS calculates the Euclidean distances from the sampling point to each neighbor point. With these distances, neighbor points in the local region are reorganized to establish multiple triangles to retain as much information. To solve the challenge (ii), a curvature-based geometric descriptor <inline-formula> <tex-math notation="LaTeX">$\text {(CGD)}$ </tex-math></inline-formula> is developed. It calculates the Euclidean distance and angle between the points within established triangles. Further, the CGD constructs a curvature circle for each triangle and calculate the curvature radius which is highly sensitive to small local shape changes. Even Euclidean distances and angles are similar, the CGD can maintain high uniqueness for local regions. Experiments on ModelNet40, ScanObjectNN, and ShapeNet have proved that the proposed approach outperforms other state-of-the-art methods. |
| format | Article |
| id | doaj-art-de66df1b403843f48eb80fcafbec572e |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-de66df1b403843f48eb80fcafbec572e2025-01-21T00:00:58ZengIEEEIEEE Access2169-35362025-01-0113104321044610.1109/ACCESS.2025.352843510838555Rotation-Invariant Convolution With Point Sort and Curvature Radius for Point Cloud Classification and SegmentationZhao Shen0https://orcid.org/0009-0009-6930-9675Xin Jia1https://orcid.org/0000-0003-2289-8934Jinglei Zhang2https://orcid.org/0000-0003-1438-6568School of Electrical Engineering and Automation, Tianjin University of Technology, Tianjin, ChinaEngineering Training Center, Tianjin University of Technology, Tianjin, ChinaSchool of Electrical Engineering and Automation, Tianjin University of Technology, Tianjin, ChinaRecently, the distance-based and angle-based geometric descriptors and local reference axes have been used widely to explore the rotation invariance of point clouds. However, they tend to encounter with two challenges. (i) Similar distances and angles among different points would lead to ambiguous descriptions of local regions. (ii) Establishing a local reference axis may reduce the number of neighbor points, resulting in information loss in local regions. To this end, a Rotation-invariant Convolution with Point Sorting and Curvature Radius <inline-formula> <tex-math notation="LaTeX">$\text {(RCPC)}$ </tex-math></inline-formula> is proposed. Firstly, to solve the challenge (i), a neighbor point sorting module <inline-formula> <tex-math notation="LaTeX">$\text {(NPS)}$ </tex-math></inline-formula> is introduced. Neighbor points on the local tangent disk are sorted according to the local reference axis at the first step. When neighbor points occlude each other along the local reference axis direction, NPS calculates the Euclidean distances from the sampling point to each neighbor point. With these distances, neighbor points in the local region are reorganized to establish multiple triangles to retain as much information. To solve the challenge (ii), a curvature-based geometric descriptor <inline-formula> <tex-math notation="LaTeX">$\text {(CGD)}$ </tex-math></inline-formula> is developed. It calculates the Euclidean distance and angle between the points within established triangles. Further, the CGD constructs a curvature circle for each triangle and calculate the curvature radius which is highly sensitive to small local shape changes. Even Euclidean distances and angles are similar, the CGD can maintain high uniqueness for local regions. Experiments on ModelNet40, ScanObjectNN, and ShapeNet have proved that the proposed approach outperforms other state-of-the-art methods.https://ieeexplore.ieee.org/document/10838555/3D point cloudrotation-invariant convolutionpoint sortcurvature radius |
| spellingShingle | Zhao Shen Xin Jia Jinglei Zhang Rotation-Invariant Convolution With Point Sort and Curvature Radius for Point Cloud Classification and Segmentation IEEE Access 3D point cloud rotation-invariant convolution point sort curvature radius |
| title | Rotation-Invariant Convolution With Point Sort and Curvature Radius for Point Cloud Classification and Segmentation |
| title_full | Rotation-Invariant Convolution With Point Sort and Curvature Radius for Point Cloud Classification and Segmentation |
| title_fullStr | Rotation-Invariant Convolution With Point Sort and Curvature Radius for Point Cloud Classification and Segmentation |
| title_full_unstemmed | Rotation-Invariant Convolution With Point Sort and Curvature Radius for Point Cloud Classification and Segmentation |
| title_short | Rotation-Invariant Convolution With Point Sort and Curvature Radius for Point Cloud Classification and Segmentation |
| title_sort | rotation invariant convolution with point sort and curvature radius for point cloud classification and segmentation |
| topic | 3D point cloud rotation-invariant convolution point sort curvature radius |
| url | https://ieeexplore.ieee.org/document/10838555/ |
| work_keys_str_mv | AT zhaoshen rotationinvariantconvolutionwithpointsortandcurvatureradiusforpointcloudclassificationandsegmentation AT xinjia rotationinvariantconvolutionwithpointsortandcurvatureradiusforpointcloudclassificationandsegmentation AT jingleizhang rotationinvariantconvolutionwithpointsortandcurvatureradiusforpointcloudclassificationandsegmentation |