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.
@article{arxiv.2605.27178,
title = {FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation},
author = {Zihui Zhang and Zhixuan Sun and Yafei Yang and Jinxi Li and Jiahao Chen and Bo Yang},
journal= {arXiv preprint arXiv:2605.27178},
year = {2026}
}
Comments
ICML 2026. Zihui and Zhixuan are co-first authors. Code and data are available at: https://github.com/vLAR-group/FoundObj