IL3D：用于LLM驱动的三维场景生成的大规模室内布局数据集
IL3D: A Large-Scale Indoor Layout Dataset for LLM-Driven 3D Scene Generation
AI总结：
本文提出IL3D大规模室内布局数据集，含27,816个布局和29,215个三维资产，支持LLM驱动的场景生成，经监督微调显著提升泛化性能，并支持多模态导出，推动具身智能研究。
摘要：
在本研究中，我们提出了IL3D，一个为大型语言模型（LLM）驱动的三维场景生成而精心设计的大规模数据集，解决了室内布局设计中对多样化、高质量训练数据的迫切需求。IL3D包含18种常见房间类型的27,816个室内布局以及29,215个高保真三维物体资产的库，并配有实例级自然语言注释，以支持视觉-语言任务的稳健多模态学习。我们建立了严格的基准来评估LLM驱动的场景生成。实验结果表明，在IL3D上对LLM进行监督微调（SFT）显著提高了泛化能力，并超过了在其他数据集上进行SFT的性能。IL3D提供灵活的多模态数据导出功能，包括点云、三维边界框、多视图图像、深度图、法线图和语义掩码，使其能够无缝适应各种视觉任务。作为一个多功能且稳健的资源，IL3D通过提供高保真场景数据以支持具身智能体的环境感知任务，显著推进了三维场景生成和具身智能的研究。
英文摘要：
In this study, we present IL3D, a large-scale dataset meticulously designed for large language model (LLM)-driven 3D scene generation, addressing the pressing demand for diverse, high-quality training data in indoor layout design. Comprising 27,816 indoor layouts across 18 prevalent room types and a library of 29,215 high-fidelity 3D object assets, IL3D is enriched with instance-level natural language annotations to support robust multimodal learning for vision-language tasks. We establish rigorous benchmarks to evaluate LLM-driven scene generation. Experimental results show that supervised fine-tuning (SFT) of LLMs on IL3D significantly improves generalization and surpasses the performance of SFT on other datasets. IL3D offers flexible multimodal data export capabilities, including point clouds, 3D bounding boxes, multiview images, depth maps, normal maps, and semantic masks, enabling seamless adaptation to various visual tasks. As a versatile and robust resource, IL3D significantly advances research in 3D scene generation and embodied intelligence, by providing high-fidelity scene data to support environment perception tasks of embodied agents.
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。
