SceneCOT: 在3D场景中引导链式推理
SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes
AI总结：
本文提出SCENECOT框架，通过分解复杂任务并构建视觉线索，首次在3D场景中实现 grounded 链式推理，提升场景理解的推理能力。
摘要：
现有针对3D大语言模型（LLMs）的研究仍难以实现 grounded 的问答，主要由于对人类样式的场景-物体 grounded 推理机制的探索不足。本文通过提出一个新颖的框架来弥合这一差距。我们首先引入了一种在3D场景中的 grounded 链式推理方法（SCENECOT），将复杂的推理任务分解为更简单和可管理的问题，并基于多模态专家模块构建相应的视觉线索。为了实现这种方法，我们开发了SCENECOT-185K，这是首个大规模的 grounded CoT推理数据集，包含185,000个高质量实例。在各种复杂的3D场景推理基准上的广泛实验表明，我们的新框架在高 grounding-QA 一致性的情况下实现了强大的性能。据我们所知，这是首次将CoT推理成功应用于3D场景理解，使能够逐步实现人类样式的推理，并展示了向更广泛的3D场景理解场景扩展的潜力。
英文摘要：
Existing research on 3D Large Language Models (LLMs) still struggles to achieve grounded question-answering, primarily due to the under-exploration of the mechanism of human-like scene-object grounded reasoning. This paper bridges the gap by presenting a novel framework. We first introduce a grounded Chain-of-Thought reasoning method in 3D scenes (SCENECOT), decoupling a complex reasoning task into simpler and manageable problems, and building corresponding visual clues based on multimodal expert modules. To enable such a method, we develop SCENECOT-185K, the first large-scale grounded CoT reasoning dataset, consisting of 185K high-quality instances. Extensive experiments across various complex 3D scene reasoning benchmarks demonstrate that our new framework achieves strong performance with high grounding-QA coherence. To the best of our knowledge, this is the first successful application of CoT reasoning to 3D scene understanding, enabling step-by-step human-like reasoning and showing potential for extension to broader 3D scene understanding scenarios.
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。
