SceneWeaver：基于可扩展自反思智能体的全能3D场景合成
SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent
AI总结：
SceneWeaver提出一个可扩展自反思智能体框架，通过语言模型规划器选择工具并迭代优化，统一多种场景合成范式，在物理、视觉和语义指标上超越现有方法，并泛化到复杂开放词汇场景。
摘要：
随着具身智能的兴起，室内场景合成变得越来越重要，它需要不仅视觉上逼真，而且物理上合理、功能上多样的3D环境。尽管近期方法在视觉保真度上取得了进展，但它们往往局限于固定的场景类别，缺乏足够的物体级细节和物理一致性，并且难以与复杂的用户指令对齐。在这项工作中，我们提出了SceneWeaver，一个反思型智能体框架，通过基于工具的迭代细化统一了多种场景合成范式。其核心是，SceneWeaver采用基于语言模型的规划器，从一套可扩展的场景生成工具中选择工具，这些工具涵盖从数据驱动的生成模型到基于视觉和基于LLM的方法，并依据对物理合理性、视觉真实性和与用户输入的语义对齐的自评估进行指导。这种闭环的“推理-行动-反思”设计使智能体能够识别语义不一致性，调用针对性工具，并在连续迭代中更新环境。在常见和开放词汇房间类型上的大量实验表明，SceneWeaver不仅在物理、视觉和语义指标上优于先前方法，而且能有效泛化到具有多样指令的复杂场景，标志着向通用3D环境生成迈出了一步。项目网站：https://scene-weaver.github.io/。
英文摘要：
Indoor scene synthesis has become increasingly important with the rise of Embodied AI, which requires 3D environments that are not only visually realistic but also physically plausible and functionally diverse. While recent approaches have advanced visual fidelity, they often remain constrained to fixed scene categories, lack sufficient object-level detail and physical consistency, and struggle to align with complex user instructions. In this work, we present SceneWeaver, a reflective agentic framework that unifies diverse scene synthesis paradigms through tool-based iterative refinement. At its core, SceneWeaver employs a language model-based planner to select from a suite of extensible scene generation tools, ranging from data-driven generative models to visual- and LLM-based methods, guided by self-evaluation of physical plausibility, visual realism, and semantic alignment with user input. This closed-loop reason-act-reflect design enables the agent to identify semantic inconsistencies, invoke targeted tools, and update the environment over successive iterations. Extensive experiments on both common and open-vocabulary room types demonstrate that SceneWeaver not only outperforms prior methods on physical, visual, and semantic metrics, but also generalizes effectively to complex scenes with diverse instructions, marking a step toward general-purpose 3D environment generation. Project website: https://scene-weaver.github.io/.
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。
