Ground3D-LMM：基于LMM的细粒度3D点接地与空间推理
Ground3D-LMM: Fine-Grained 3D Point Grounding and Spatial Reasoning with LMM
AI总结：
研究3D环境自然语言查询的可操作性问题，提出Ground3D-LMM统一模型，以点云等为输入，支持3D空间对话，能给出基于点的响应和度量数值输出，通过定义新任务、引入数据集验证，为3D对话理解提供强大基线。
摘要：
关于3D环境的自然语言查询，当响应可验证且具有度量时变得可操作。可验证性需要明确接地到所指的3D区域，而度量答案报告实际单位的物理测量值。现有3D大型多模态模型（LMMs）方法有限，本文提出Ground3D-LMM统一模型，以点云等为输入，支持3D空间对话，能给出基于点的响应和度量数值输出。为评估接地与测量，定义3D接地测量任务，引入大规模数据集及手动验证测试集。实验表明该模型为有接地、度量感知的3D对话理解提供了强大基线，数据集和模型公开可用。
英文摘要：
Natural-language queries about 3D environments become actionable when responses are verifiable and metric. Verifiability requires explicit grounding to the referred 3D region, while metric answers report physical measurements in real-world units (e.g., size, thickness, clearance, and distance). Existing 3D large multimodal models (LMMs) approaches remain limited: conversational systems typically respond without explicit 3D grounding, while 3D grounding models are not designed for interactive, metric-aware dialogue. In this paper, we present Ground3D-LMM, a unified model that takes a point cloud and an optional RGB image as input and supports 3D spatial conversation with (i) point-grounded responses and (ii) metric numeric outputs at both object and part granularity, including multi-object queries. To evaluate this intersection of grounding and measurement, we define the 3D Grounded Measurement task, which requires predicting the referred 3D region and the corresponding metric quantities in real-world units. We introduce a large-scale dataset built on ScanNet and ScanNet++ datasets with dense object and part annotations and roughly 2.5M question-answer pairs spanning eight tasks, along with a manually verified test set. Extensive experiments on multiple datasets and tasks show that our proposed Ground3D-LMM model provides a strong baseline for grounded, metric-aware 3D conversational understanding. Our dataset and model are publicly available.
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。
