Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.01407 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929265515167744 |
|---|---|
| author | Gyawali, Dipesh Zhang, Jian Karki, BB |
| author_facet | Gyawali, Dipesh Zhang, Jian Karki, BB |
| contents | Point cloud segmentation, which helps us understand the environment of specific structures and objects, can be performed in class-specific and class-agnostic ways. We propose a novel region-based transformer model called Region-Transformer for performing class-agnostic point cloud segmentation. The model utilizes a region-growth approach and self-attention mechanism to iteratively expand or contract a region by adding or removing points. It is trained on simulated point clouds with instance labels only, avoiding semantic labels. Attention-based networks have succeeded in many previous methods of performing point cloud segmentation. However, a region-growth approach with attention-based networks has yet to be used to explore its performance gain. To our knowledge, we are the first to use a self-attention mechanism in a region-growth approach. With the introduction of self-attention to region-growth that can utilize local contextual information of neighborhood points, our experiments demonstrate that the Region-Transformer model outperforms previous class-agnostic and class-specific methods on indoor datasets regarding clustering metrics. The model generalizes well to large-scale scenes. Key advantages include capturing long-range dependencies through self-attention, avoiding the need for semantic labels during training, and applicability to a variable number of objects. The Region-Transformer model represents a promising approach for flexible point cloud segmentation with applications in robotics, digital twinning, and autonomous vehicles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01407 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Region-Transformer: Self-Attention Region Based Class-Agnostic Point Cloud Segmentation Gyawali, Dipesh Zhang, Jian Karki, BB Computer Vision and Pattern Recognition Artificial Intelligence Robotics Point cloud segmentation, which helps us understand the environment of specific structures and objects, can be performed in class-specific and class-agnostic ways. We propose a novel region-based transformer model called Region-Transformer for performing class-agnostic point cloud segmentation. The model utilizes a region-growth approach and self-attention mechanism to iteratively expand or contract a region by adding or removing points. It is trained on simulated point clouds with instance labels only, avoiding semantic labels. Attention-based networks have succeeded in many previous methods of performing point cloud segmentation. However, a region-growth approach with attention-based networks has yet to be used to explore its performance gain. To our knowledge, we are the first to use a self-attention mechanism in a region-growth approach. With the introduction of self-attention to region-growth that can utilize local contextual information of neighborhood points, our experiments demonstrate that the Region-Transformer model outperforms previous class-agnostic and class-specific methods on indoor datasets regarding clustering metrics. The model generalizes well to large-scale scenes. Key advantages include capturing long-range dependencies through self-attention, avoiding the need for semantic labels during training, and applicability to a variable number of objects. The Region-Transformer model represents a promising approach for flexible point cloud segmentation with applications in robotics, digital twinning, and autonomous vehicles. |
| title | Region-Transformer: Self-Attention Region Based Class-Agnostic Point Cloud Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2403.01407 |