让机器人精准识别小而精细的物体并准确定位，同时判断目标是否缺失。
OVIP-SG: Open-Vocabulary Instance-Preserving Scene Graphs for Mapping and Retrieval of Small, Fine-Grained Objects
- 用视觉语言模型识别场景特有类别，保持物体实例完整。
- 搜索区域缩小至21.8%，物体存在性判断准确率达77.3%。
- 适合需要细粒度感知与可靠检索的机器人导航任务。
将开放词汇感知融入基于物体的三维场景图是把双刃剑。尽管视觉语言检测器能恢复长尾类别和被封闭集模型忽略的小而精细物体，但也容易分割大表面或合并小物体，破坏实例一致性并损害建图精度。现有方法难以检索未映射的目标或判断查询物体是否存在，阻碍了鲁棒的具身开放式导航与探索。本文提出OVIP-SG，一个统一框架，实现实例保持的语义建图、功能分区与语言引导的小型精细物体检索。该框架利用视觉语言模型（VLM）枚举场景特定类别以实现鲁棒的开放世界检测。对称3D交并比关联与面积加权特征融合保留小型独立实例；由VLM推断的物体功能将场景划分为紧凑的功能搜索区域。四阶段级联检索管道进一步引入体素投票，并通过探索覆盖度判断目标是否存在。在Replica数据集上，统一评估协议下，OVIP-SG相较ConceptGraphs提升6.31点类均准确率（mAcc）与5.15点频率加权mIoU（F-mIoU），达到0.398的类无关原生实例全景质量（PQ）。搜索面积缩减至室内空间的21.8%，物体存在性分类平衡准确率达0.773。真实机器人实验验证了其实际有效性。代码已开源。
原文摘要 · Abstract (English)
Integrating open-vocabulary perception into object-level 3D scene graphs is a double-edged sword. While vision-language detectors recover long-tail categories and small, fine-grained objects overlooked by closed-set models, they also tend to fragment large surfaces and merge small objects into larger neighboring objects, compromising instance-level consistency and undermining mapping fidelity. Moreover, existing methods struggle to retrieve previously unmapped targets or determine whether a queried object is absent, hindering robust embodied open-world navigation and exploration. We present OVIP-SG, a unified framework for instance-preserving semantic mapping, functional scene partitioning, and language-guided small, fine-grained object retrieval. OVIP-SG uses a vision-language model (VLM) to enumerate scene-specific categories for robust open-world detection. Symmetric 3D Intersection over Union (IoU) association and area-weighted feature fusion preserve small independent instances, while VLM-inferred object functions partition scenes into compact functional search regions. A four-stage cascaded retrieval pipeline further incorporates voxel voting and determines target absence from exploration coverage. Under a unified evaluation protocol on Replica, OVIP-SG outperforms ConceptGraphs by 6.31 points in class-mean accuracy (mAcc) and 5.15 points in frequency-weighted mIoU (F-mIoU) while achieving a class-agnostic native-instance Panoptic Quality (PQ) of 0.398. It reduces the search area to 21.8% of the indoor floor space and reaches 0.773 balanced accuracy for object-presence classification. Real-world robotic experiments further demonstrate its practical effectiveness. Code is available at https://github.com/Agibot-Spatial-Intelligence/OVIP-SG.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。