Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916936077541376 |
|---|---|
| author | Saeid, Mohammad Salarpour, Amir MohajerAnsari, Pedram |
| author_facet | Saeid, Mohammad Salarpour, Amir MohajerAnsari, Pedram |
| contents | The classification of 3D point clouds is crucial for applications such as autonomous driving, robotics, and augmented reality. However, the commonly used ModelNet40 dataset suffers from limitations such as inconsistent labeling, 2D data, size mismatches, and inadequate class differentiation, which hinder model performance. This paper introduces ModelNet-R, a meticulously refined version of ModelNet40 designed to address these issues and serve as a more reliable benchmark. Additionally, this paper proposes Point-SkipNet, a lightweight graph-based neural network that leverages efficient sampling, neighborhood grouping, and skip connections to achieve high classification accuracy with reduced computational overhead. Extensive experiments demonstrate that models trained in ModelNet-R exhibit significant performance improvements. Notably, Point-SkipNet achieves state-of-the-art accuracy on ModelNet-R with a substantially lower parameter count compared to contemporary models. This research highlights the crucial role of dataset quality in optimizing model efficiency for 3D point cloud classification. For more details, see the code at: https://github.com/m-saeid/ModeNetR_PointSkipNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05198 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet Saeid, Mohammad Salarpour, Amir MohajerAnsari, Pedram Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics The classification of 3D point clouds is crucial for applications such as autonomous driving, robotics, and augmented reality. However, the commonly used ModelNet40 dataset suffers from limitations such as inconsistent labeling, 2D data, size mismatches, and inadequate class differentiation, which hinder model performance. This paper introduces ModelNet-R, a meticulously refined version of ModelNet40 designed to address these issues and serve as a more reliable benchmark. Additionally, this paper proposes Point-SkipNet, a lightweight graph-based neural network that leverages efficient sampling, neighborhood grouping, and skip connections to achieve high classification accuracy with reduced computational overhead. Extensive experiments demonstrate that models trained in ModelNet-R exhibit significant performance improvements. Notably, Point-SkipNet achieves state-of-the-art accuracy on ModelNet-R with a substantially lower parameter count compared to contemporary models. This research highlights the crucial role of dataset quality in optimizing model efficiency for 3D point cloud classification. For more details, see the code at: https://github.com/m-saeid/ModeNetR_PointSkipNet. |
| title | Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics |
| url | https://arxiv.org/abs/2509.05198 |