Category-Agnostic Pose Estimation for Point Clouds
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914710917480448 |
|---|---|
| author | Liu, Bowen Liu, Wei Chen, Siang Xie, Pengwei Wang, Guijin |
| author_facet | Liu, Bowen Liu, Wei Chen, Siang Xie, Pengwei Wang, Guijin |
| contents | The goal of object pose estimation is to visually determine the pose of a specific object in the RGB-D input. Unfortunately, when faced with new categories, both instance-based and category-based methods are unable to deal with unseen objects of unseen categories, which is a challenge for pose estimation. To address this issue, this paper proposes a method to introduce geometric features for pose estimation of point clouds without requiring category information. The method is based only on the patch feature of the point cloud, a geometric feature with rotation invariance. After training without category information, our method achieves as good results as other category-based methods. Our method successfully achieved pose annotation of no category information instances on the CAMERA25 dataset and ModelNet40 dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07437 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Category-Agnostic Pose Estimation for Point Clouds Liu, Bowen Liu, Wei Chen, Siang Xie, Pengwei Wang, Guijin Computer Vision and Pattern Recognition The goal of object pose estimation is to visually determine the pose of a specific object in the RGB-D input. Unfortunately, when faced with new categories, both instance-based and category-based methods are unable to deal with unseen objects of unseen categories, which is a challenge for pose estimation. To address this issue, this paper proposes a method to introduce geometric features for pose estimation of point clouds without requiring category information. The method is based only on the patch feature of the point cloud, a geometric feature with rotation invariance. After training without category information, our method achieves as good results as other category-based methods. Our method successfully achieved pose annotation of no category information instances on the CAMERA25 dataset and ModelNet40 dataset. |
| title | Category-Agnostic Pose Estimation for Point Clouds |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.07437 |