FunFact：通过因子图推理构建概率功能3D场景图
FunFact: Building Probabilistic Functional 3D Scene Graphs via Factor-Graph Reasoning
将功能关系建模为因子图变量，结合LLM常识先验与几何先验进行联合概率推理，可提升开放词表场景图中关系发现的召回率与置信度校准，适用于需要场景级推理的3D理解任务。
原文依据 These candidates are converted into factor graph variables and constrained by both LLM-derived common-sense priors and geometric priors.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期3D场景理解的研究正从纯空间分析转向功能场景理解。然而，现有方法往往孤立地考虑物体对之间的功能关系，未能捕捉人类用于消解歧义的场景级相互依赖。我们提出FunFact，一个从带位姿的RGB-D图像构建概率开放词表功能3D场景图的框架。FunFact首先构建以物体和部件为中心的3D地图，并利用基础模型提出语义上合理的功能关系。这些候选关系被转换为因子图变量，并受LLM衍生的常识先验和几何先验的共同约束。该公式化方法能够对所有功能边及其边缘概率进行联合概率推理，从而产生校准更好的置信度分数。为了对该设定进行基准测试，我们引入了FunThor，一个基于AI2-THOR的合成数据集，具有部件级几何和基于规则的功能标注。在SceneFun3D、FunGraph3D和FunThor上的实验表明，FunFact提升了节点和关系发现的召回率，并显著降低了歧义关系的校准误差，凸显了整体概率建模对功能场景理解的优势。项目页面见https://funfact-scenegraph.github.io/。
英文原文摘要 1370 字符
Recent work in 3D scene understanding is moving beyond purely spatial analysis toward functional scene understanding. However, existing methods often consider functional relationships between object pairs in isolation, failing to capture the scene-wide interdependence that humans use to resolve ambiguity. We introduce FunFact, a framework for constructing probabilistic open-vocabulary functional 3D scene graphs from posed RGB-D images. FunFact first builds an object- and part-centric 3D map and uses foundation models to propose semantically plausible functional relations. These candidates are converted into factor graph variables and constrained by both LLM-derived common-sense priors and geometric priors. This formulation enables joint probabilistic inference over all functional edges and their marginals, yielding substantially better calibrated confidence scores. To benchmark this setting, we introduce FunThor, a synthetic dataset based on AI2-THOR with part-level geometry and rule-based functional annotations. Experiments on SceneFun3D, FunGraph3D, and FunThor show that FunFact improves node and relation discovery recall and significantly reduces calibration error for ambiguous relations, highlighting the benefits of holistic probabilistic modeling for functional scene understanding. See our project page at https://funfact-scenegraph.github.io/.