FOMO-3D: Using Vision Foundation Models for Long-Tailed 3D Object Detection
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_ | 1866911499242438656 |
|---|---|
| author | Yang, Anqi Joyce Tu, James Dvornik, Nikita Li, Enxu Urtasun, Raquel |
| author_facet | Yang, Anqi Joyce Tu, James Dvornik, Nikita Li, Enxu Urtasun, Raquel |
| contents | In order to navigate complex traffic environments, self-driving vehicles must recognize many semantic classes pertaining to vulnerable road users or traffic control devices. However, many safety-critical objects (e.g., construction worker) appear infrequently in nominal traffic conditions, leading to a severe shortage of training examples from driving data alone. Recent vision foundation models, which are trained on a large corpus of data, can serve as a good source of external prior knowledge to improve generalization. We propose FOMO-3D, the first multi-modal 3D detector to leverage vision foundation models for long-tailed 3D detection. Specifically, FOMO-3D exploits rich semantic and depth priors from OWLv2 and Metric3Dv2 within a two-stage detection paradigm that first generates proposals with a LiDAR-based branch and a novel camera-based branch, and refines them with attention especially to image features from OWL. Evaluations on real-world driving data show that using rich priors from vision foundation models with careful multi-modal fusion designs leads to large gains for long-tailed 3D detection. Project website is at https://waabi.ai/fomo3d/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_08611 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FOMO-3D: Using Vision Foundation Models for Long-Tailed 3D Object Detection Yang, Anqi Joyce Tu, James Dvornik, Nikita Li, Enxu Urtasun, Raquel Computer Vision and Pattern Recognition Robotics In order to navigate complex traffic environments, self-driving vehicles must recognize many semantic classes pertaining to vulnerable road users or traffic control devices. However, many safety-critical objects (e.g., construction worker) appear infrequently in nominal traffic conditions, leading to a severe shortage of training examples from driving data alone. Recent vision foundation models, which are trained on a large corpus of data, can serve as a good source of external prior knowledge to improve generalization. We propose FOMO-3D, the first multi-modal 3D detector to leverage vision foundation models for long-tailed 3D detection. Specifically, FOMO-3D exploits rich semantic and depth priors from OWLv2 and Metric3Dv2 within a two-stage detection paradigm that first generates proposals with a LiDAR-based branch and a novel camera-based branch, and refines them with attention especially to image features from OWL. Evaluations on real-world driving data show that using rich priors from vision foundation models with careful multi-modal fusion designs leads to large gains for long-tailed 3D detection. Project website is at https://waabi.ai/fomo3d/. |
| title | FOMO-3D: Using Vision Foundation Models for Long-Tailed 3D Object Detection |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2603.08611 |