三维场景图中语义不确定性的层次聚合

中文摘要 AI 辅助

开放词汇三维场景图（3DSGs）将每个对象节点锚定在视觉-语言嵌入中，然而它们将每个条目记录为同等确定，因此查询地图的机器人无法分辨哪些条目不可靠。语义不确定性的估计器可以提供这种区分，但它们需要重复采样模型、训练或保留标签，而这些在部署系统查询时均不可用。我们提出一个框架，利用检测器置信度和3DSG已存储的嵌入，将其转换为条目正确的概率，并通过包含层次将该概率传播到房间包含查询类别的信念中。四个信号，每个信号与它所指示的对象级错误配对，在视觉-语言模型学习的对数尺度上转换为概率，并以封闭形式组合，无需额外的感知或训练。共享检测器和词汇表的对象会一起失败，因此框架在完全相关极限下聚合它们，而在独立假设下的聚合会将一次重复错误视为重复证据。在HM3DSem上针对最先进的三维场景图系统进行评估，该框架提高了对象检索性能，并降低了其读取图的房间级断言的错误。

英文摘要

Open-vocabulary 3D Scene Graphs (3DSGs) ground each object node in a vision-language embedding, yet they record every entry as equally certain, so a robot querying the map cannot tell which of its entries are unreliable. Estimators of semantic uncertainty could supply that distinction, but they require repeated sampling of a model, training, or held-out labels, none of which are available to a deployed system at query time. We present a framework that exploits the detector confidence and the embeddings a 3DSG already stores, converts them into a probability that an entry is correct, and propagates that probability through the containment hierarchy into a belief that a room contains a queried class. Four signals, each paired with the object-level error it indicates, are converted to probabilities at the logit scale learned by the vision-language model and combined in closed form with no additional perception or training. Objects sharing a detector and a vocabulary fail together, so the framework aggregates them in the fully correlated limit, where an aggregation under independence would treat one repeated error as repeated evidence. Evaluated on HM3DSem against a state-of-the-art 3DSG system, the framework improves object retrieval and lowers the error of the room-level assertions of the graph it reads.

发表机构

• University of Turku（图尔库大学）
• Aragón Institute of Technology (ITA)（阿拉贡技术研究所）
• University of Zaragoza（萨拉戈萨大学）

机构由 AI 辅助整理，请以论文原文为准。