HOG-Layout：基于视觉语言模型的分层三维场景生成、优化与编辑
HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language Models
用 LLM/VLM 加 RAG 从文本生成分层 3D 场景布局，并配物理一致性优化模块与分层表示实现实时编辑，可作为具身智能与 VR 场景合成的可复用管线。
原文依据 adopts a hierarchical representation to enhance inference and optimization, achieving real-time editing
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维布局生成与编辑在具身智能与沉浸式 VR 交互中起着关键作用。然而，人工创建需要繁琐的劳动，而数据驱动的生成往往缺乏多样性。大模型的出现为三维场景合成带来了新的可能。我们提出 HOG-Layout，借助大语言模型（LLM）与视觉语言模型（VLM）实现文本驱动的分层场景生成、优化与实时场景编辑。HOG-Layout 通过检索增强生成（RAG）技术提升场景语义一致性与合理性，引入优化模块以增强物理一致性，并采用分层表示来增强推理与优化，从而实现实时编辑。实验结果表明，与现有基线相比，HOG-Layout 能生成更合理的环境，同时支持快速、直观的场景编辑。
英文原文摘要 940 字符
3D layout generation and editing play a crucial role in Embodied AI and immersive VR interaction. However, manual creation requires tedious labor, while data-driven generation often lacks diversity. The emergence of large models introduces new possibilities for 3D scene synthesis. We present HOG-Layout that enables text-driven hierarchical scene generation, optimization and real-time scene editing with large language models (LLMs) and vision-language models (VLMs). HOG-Layout improves scene semantic consistency and plausibility through retrieval-augmented generation (RAG) technology, incorporates an optimization module to enhance physical consistency, and adopts a hierarchical representation to enhance inference and optimization, achieving real-time editing. Experimental results demonstrate that HOG-Layout produces more reasonable environments compared with existing baselines, while supporting fast and intuitive scene editing.