FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation
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_ | 1866917536586530816 |
|---|---|
| author | Zhang, Zihui Sun, Zhixuan Yang, Yafei Li, Jinxi Chen, Jiahao Yang, Bo |
| author_facet | Zhang, Zihui Sun, Zhixuan Yang, Yafei Li, Jinxi Chen, Jiahao Yang, Bo |
| contents | We address the challenging task of 3D object segmentation in complex scene point clouds without relying on any scene-level human annotations during training. Existing methods are typically constrained to identifying simple objects, primarily due to insufficient object priors in the learning process. In this paper, we present FoundObj, a novel framework featuring a superpoint-based object discovery agent that incrementally merges suitable neighboring superpoints, guided by our innovative semantic and geometric reward modules. These modules synergistically leverage semantic and geometric priors from self-supervised 2D/3D foundation models, providing complementary feedback to the object discovery agent and enabling robust identification of multi-class objects through reinforcement learning. Extensive experiments on diverse benchmarks demonstrate that our approach consistently outperforms existing baselines. Notably, our method exhibits strong generalization in zero-shot and long-tail scenarios, underscoring its potential for scalable, label-free 3D object segmentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_27178 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation Zhang, Zihui Sun, Zhixuan Yang, Yafei Li, Jinxi Chen, Jiahao Yang, Bo Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics We address the challenging task of 3D object segmentation in complex scene point clouds without relying on any scene-level human annotations during training. Existing methods are typically constrained to identifying simple objects, primarily due to insufficient object priors in the learning process. In this paper, we present FoundObj, a novel framework featuring a superpoint-based object discovery agent that incrementally merges suitable neighboring superpoints, guided by our innovative semantic and geometric reward modules. These modules synergistically leverage semantic and geometric priors from self-supervised 2D/3D foundation models, providing complementary feedback to the object discovery agent and enabling robust identification of multi-class objects through reinforcement learning. Extensive experiments on diverse benchmarks demonstrate that our approach consistently outperforms existing baselines. Notably, our method exhibits strong generalization in zero-shot and long-tail scenarios, underscoring its potential for scalable, label-free 3D object segmentation. |
| title | FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics |
| url | https://arxiv.org/abs/2605.27178 |