Training-free zero-shot 3D symmetry detection with visual features back-projected to geometry
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_ | 1866912403775553536 |
|---|---|
| author | Aguirre, Isaac Sipiran, Ivan |
| author_facet | Aguirre, Isaac Sipiran, Ivan |
| contents | We present a simple yet effective training-free approach for zero-shot 3D symmetry detection that leverages visual features from foundation vision models such as DINOv2. Our method extracts features from rendered views of 3D objects and backprojects them onto the original geometry. We demonstrate the symmetric invariance of these features and use them to identify reflection-symmetry planes through a proposed algorithm. Experiments on a subset of ShapeNet demonstrate that our approach outperforms both traditional geometric methods and learning-based approaches without requiring any training data. Our work demonstrates how foundation vision models can help in solving complex 3D geometric problems such as symmetry detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_24162 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Training-free zero-shot 3D symmetry detection with visual features back-projected to geometry Aguirre, Isaac Sipiran, Ivan Computer Vision and Pattern Recognition We present a simple yet effective training-free approach for zero-shot 3D symmetry detection that leverages visual features from foundation vision models such as DINOv2. Our method extracts features from rendered views of 3D objects and backprojects them onto the original geometry. We demonstrate the symmetric invariance of these features and use them to identify reflection-symmetry planes through a proposed algorithm. Experiments on a subset of ShapeNet demonstrate that our approach outperforms both traditional geometric methods and learning-based approaches without requiring any training data. Our work demonstrates how foundation vision models can help in solving complex 3D geometric problems such as symmetry detection. |
| title | Training-free zero-shot 3D symmetry detection with visual features back-projected to geometry |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.24162 |