Unlocking Hidden Potential in Point Cloud Networks with Attention-Guided Grouping-Feature Coordination
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_ | 1866908549359075328 |
|---|---|
| author | Xie, Shangzhuo Yang, Qianqian |
| author_facet | Xie, Shangzhuo Yang, Qianqian |
| contents | Point cloud analysis has evolved with diverse network architectures, while existing works predominantly focus on introducing novel structural designs. However, conventional point-based architectures - processing raw points through sequential sampling, grouping, and feature extraction layers - demonstrate underutilized potential. We notice that substantial performance gains can be unlocked through strategic module integration rather than structural modifications. In this paper, we propose the Grouping-Feature Coordination Module (GF-Core), a lightweight separable component that simultaneously regulates both grouping layer and feature extraction layer to enable more nuanced feature aggregation. Besides, we introduce a self-supervised pretraining strategy specifically tailored for point-based inputs to enhance model robustness in complex point cloud analysis scenarios. On ModelNet40 dataset, our method elevates baseline networks to 94.0% accuracy, matching advanced frameworks' performance while preserving architectural simplicity. On three variants of the ScanObjectNN dataset, we obtain improvements of 2.96%, 6.34%, and 6.32% respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16639 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unlocking Hidden Potential in Point Cloud Networks with Attention-Guided Grouping-Feature Coordination Xie, Shangzhuo Yang, Qianqian Computer Vision and Pattern Recognition Point cloud analysis has evolved with diverse network architectures, while existing works predominantly focus on introducing novel structural designs. However, conventional point-based architectures - processing raw points through sequential sampling, grouping, and feature extraction layers - demonstrate underutilized potential. We notice that substantial performance gains can be unlocked through strategic module integration rather than structural modifications. In this paper, we propose the Grouping-Feature Coordination Module (GF-Core), a lightweight separable component that simultaneously regulates both grouping layer and feature extraction layer to enable more nuanced feature aggregation. Besides, we introduce a self-supervised pretraining strategy specifically tailored for point-based inputs to enhance model robustness in complex point cloud analysis scenarios. On ModelNet40 dataset, our method elevates baseline networks to 94.0% accuracy, matching advanced frameworks' performance while preserving architectural simplicity. On three variants of the ScanObjectNN dataset, we obtain improvements of 2.96%, 6.34%, and 6.32% respectively. |
| title | Unlocking Hidden Potential in Point Cloud Networks with Attention-Guided Grouping-Feature Coordination |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.16639 |