arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.07599cs.CV
收藏

在线分割三维物体作为实例跟踪

Online Segment Any 3D Thing as Instance Tracking

State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), CASIA(多模态人工智能系统国家重点实验室(MAIS),中国科学院自动化所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);AutoLab, School of Artificial Intelligence, Shanghai Jiao Tong University(上海交通大学人工智能学院AutoLab);Anyverse Intelligence;Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information(北京超智能多模态信息安全重点实验室);School of Information Science and Technology, ShanghaiTech University(上海科技大学信息科学与技术学院)

Hanshi Wang, Zijian Cai, Jin Gao, Yiwei Zhang, Weiming Hu, Ke Wang, Zhipeng Zhang

AI总结:

将在线3D分割重新定义为实例跟踪问题,通过时间信息传播和空间一致性学习提升具身智能体对环境的理解能力。

摘要:

在线、实时和细粒度的3D分割是具身智能体感知和理解其操作环境的基本能力。最近的进展利用预定义的对象查询来聚合从视觉基础模型(VFMs)输出中提升到3D点云中的语义信息,通过查询间的交互促进空间信息传播。然而,感知本质上是一个动态过程,使得时间理解成为这些现有查询式管道中关键但被忽视的维度。因此,为了进一步解锁具身代理的时间环境感知能力,我们的工作将在线3D分割重新概念化为一个实例跟踪问题(AutoSeg3D)。我们的核心策略是利用对象查询进行时间信息传播,其中长期实例关联促进特征和对象身份的连贯性,而短期实例更新丰富即时观察。鉴于具身机器人中的视角变化往往导致帧间物体部分可见性,这种机制帮助模型在不完整即时视图之外发展出整体物体理解。此外,我们引入了空间一致性学习以减轻VFMs中固有的碎片化问题,从而获得更全面的实例信息,以增强长期和短期时间学习的效果。通过这些稀疏对象查询所促进的时间信息交换和一致性学习,不仅增强了空间理解,也避免了密集时间点云交互带来的计算负担。我们的方法建立了一个新的最先进的状态,超过了ScanNet200上的ESAM 2.8 AP,并在ScanNet、SceneNN和3RScan数据集上实现了一致的提升。

英文摘要:

Online, real-time, and fine-grained 3D segmentation constitutes a fundamental capability for embodied intelligent agents to perceive and comprehend their operational environments. Recent advancements employ predefined object queries to aggregate semantic information from Vision Foundation Models (VFMs) outputs that are lifted into 3D point clouds, facilitating spatial information propagation through inter-query interactions. Nevertheless, perception is an inherently dynamic process, rendering temporal understanding a critical yet overlooked dimension within these prevailing query-based pipelines. Therefore, to further unlock the temporal environmental perception capabilities of embodied agents, our work reconceptualizes online 3D segmentation as an instance tracking problem (AutoSeg3D). Our core strategy involves utilizing object queries for temporal information propagation, where long-term instance association promotes the coherence of features and object identities, while short-term instance update enriches instant observations. Given that viewpoint variations in embodied robotics often lead to partial object visibility across frames, this mechanism aids the model in developing a holistic object understanding beyond incomplete instantaneous views. Furthermore, we introduce spatial consistency learning to mitigate the fragmentation problem inherent in VFMs, yielding more comprehensive instance information for enhancing the efficacy of both long-term and short-term temporal learning. The temporal information exchange and consistency learning facilitated by these sparse object queries not only enhance spatial comprehension but also circumvent the computational burden associated with dense temporal point cloud interactions. Our method establishes a new state-of-the-art, surpassing ESAM by 2.8 AP on ScanNet200 and delivering consistent gains on ScanNet, SceneNN, and 3RScan datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑