Open-vocabulary 3D scene perception in industrial environments
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911463010992128 |
|---|---|
| author | Moenck, Keno Florea, Adrian Philip Koch, Julian Schüppstuhl, Thorsten |
| author_facet | Moenck, Keno Florea, Adrian Philip Koch, Julian Schüppstuhl, Thorsten |
| contents | Autonomous vision applications in production, intralogistics, or manufacturing environments require perception capabilities beyond a small, fixed set of classes. Recent open-vocabulary methods, leveraging 2D Vision-Language Foundation Models (VLFMs), target this task but often rely on class-agnostic segmentation models pre-trained on non-industrial datasets (e.g., household scenes). In this work, we first demonstrate that such models fail to generalize, performing poorly on common industrial objects. Therefore, we propose a training-free, open-vocabulary 3D perception pipeline that overcomes this limitation. Instead of using a pre-trained model to generate instance proposals, our method simply generates masks by merging pre-computed superpoints based on their semantic features. Following, we evaluate the domain-adapted VLFM "IndustrialCLIP" on a representative 3D industrial workshop scene for open-vocabulary querying. Our qualitative results demonstrate successful segmentation of industrial objects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19823 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Open-vocabulary 3D scene perception in industrial environments Moenck, Keno Florea, Adrian Philip Koch, Julian Schüppstuhl, Thorsten Computer Vision and Pattern Recognition Autonomous vision applications in production, intralogistics, or manufacturing environments require perception capabilities beyond a small, fixed set of classes. Recent open-vocabulary methods, leveraging 2D Vision-Language Foundation Models (VLFMs), target this task but often rely on class-agnostic segmentation models pre-trained on non-industrial datasets (e.g., household scenes). In this work, we first demonstrate that such models fail to generalize, performing poorly on common industrial objects. Therefore, we propose a training-free, open-vocabulary 3D perception pipeline that overcomes this limitation. Instead of using a pre-trained model to generate instance proposals, our method simply generates masks by merging pre-computed superpoints based on their semantic features. Following, we evaluate the domain-adapted VLFM "IndustrialCLIP" on a representative 3D industrial workshop scene for open-vocabulary querying. Our qualitative results demonstrate successful segmentation of industrial objects. |
| title | Open-vocabulary 3D scene perception in industrial environments |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.19823 |