DFG-PCN: Point Cloud Completion with Degree-Flexible Point Graph
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911182098530304 |
|---|---|
| author | Shu, Zhenyu Yao, Jian Xin, Shiqing |
| author_facet | Shu, Zhenyu Yao, Jian Xin, Shiqing |
| contents | Point cloud completion is a vital task focused on reconstructing complete point clouds and addressing the incompleteness caused by occlusion and limited sensor resolution. Traditional methods relying on fixed local region partitioning, such as k-nearest neighbors, which fail to account for the highly uneven distribution of geometric complexity across different regions of a shape. This limitation leads to inefficient representation and suboptimal reconstruction, especially in areas with fine-grained details or structural discontinuities. This paper proposes a point cloud completion framework called Degree-Flexible Point Graph Completion Network (DFG-PCN). It adaptively assigns node degrees using a detail-aware metric that combines feature variation and curvature, focusing on structurally important regions. We further introduce a geometry-aware graph integration module that uses Manhattan distance for edge aggregation and detail-guided fusion of local and global features to enhance representation. Extensive experiments on multiple benchmark datasets demonstrate that our method consistently outperforms state-of-the-art approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23703 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DFG-PCN: Point Cloud Completion with Degree-Flexible Point Graph Shu, Zhenyu Yao, Jian Xin, Shiqing Graphics Computer Vision and Pattern Recognition Machine Learning Point cloud completion is a vital task focused on reconstructing complete point clouds and addressing the incompleteness caused by occlusion and limited sensor resolution. Traditional methods relying on fixed local region partitioning, such as k-nearest neighbors, which fail to account for the highly uneven distribution of geometric complexity across different regions of a shape. This limitation leads to inefficient representation and suboptimal reconstruction, especially in areas with fine-grained details or structural discontinuities. This paper proposes a point cloud completion framework called Degree-Flexible Point Graph Completion Network (DFG-PCN). It adaptively assigns node degrees using a detail-aware metric that combines feature variation and curvature, focusing on structurally important regions. We further introduce a geometry-aware graph integration module that uses Manhattan distance for edge aggregation and detail-guided fusion of local and global features to enhance representation. Extensive experiments on multiple benchmark datasets demonstrate that our method consistently outperforms state-of-the-art approaches. |
| title | DFG-PCN: Point Cloud Completion with Degree-Flexible Point Graph |
| topic | Graphics Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2509.23703 |