3EED: 在三维中万物皆 grounded
3EED: Ground Everything Everywhere in 3D
AI总结：
3EED提出一个大规模多平台多模态三维 grounding 基准测试，通过提供丰富的户外场景数据和跨平台学习技术，推动语言驱动的三维具身感知研究。
摘要：
在三维中实现视觉 grounding 是使具身智能体在开放世界环境中定位语言所指对象的关键。然而，现有基准测试局限于室内焦点、单一平台限制和小规模。我们引入了3EED，一个多平台、多模态的三维 grounding 基准测试，包含来自车辆、无人机和四足平台的RGB和激光雷达数据。我们提供了超过128,000个对象和22,000个经过验证的指代表达，覆盖多样化的户外场景——比现有数据集大10倍。我们开发了一个可扩展的标注流程，结合视觉语言模型提示和人工验证，以确保高质量的空间 grounding。为了支持跨平台学习，我们提出了平台感知的归一化和跨模态对齐技术，并建立了用于领域内和跨平台评估的基准协议。我们的发现揭示了显著的性能差距，突显了可推广的三维 grounding 的挑战和机遇。3EED数据集和基准工具包已发布，以推进未来语言驱动的三维具身感知研究。
英文摘要：
Visual grounding in 3D is the key for embodied agents to localize language-referred objects in open-world environments. However, existing benchmarks are limited to indoor focus, single-platform constraints, and small scale. We introduce 3EED, a multi-platform, multi-modal 3D grounding benchmark featuring RGB and LiDAR data from vehicle, drone, and quadruped platforms. We provide over 128,000 objects and 22,000 validated referring expressions across diverse outdoor scenes -- 10x larger than existing datasets. We develop a scalable annotation pipeline combining vision-language model prompting with human verification to ensure high-quality spatial grounding. To support cross-platform learning, we propose platform-aware normalization and cross-modal alignment techniques, and establish benchmark protocols for in-domain and cross-platform evaluations. Our findings reveal significant performance gaps, highlighting the challenges and opportunities of generalizable 3D grounding. The 3EED dataset and benchmark toolkit are released to advance future research in language-driven 3D embodied perception.
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。
