Wanderland：面向开放世界具身智能的几何落地仿真
Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI
对做视觉导航与具身评测的人，这篇给出了一个把多传感器采集、几何可靠重建与视频-3DGS 渲染串起来的 real-to-sim 管线，并量化了纯图像管线在几何上的失真如何传导到导航策略学习与评测可靠性——可直接作为闭环评测的 testbed 与消融参照。
原文依据 how geometry quality impacts novel view synthesis, and how all of these adversely affect navigation policy learning and evaluation reliability
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论可复现的闭环评测仍是视觉导航等具身智能领域的主要瓶颈。一条有前景的路径是高保真仿真，即在复杂开放世界城市环境中，将照片级真实的传感器渲染与几何落地的交互结合起来。尽管近期的视频-3DGS 方法缓解了开放世界场景采集的难度，但由于存在较大的视觉与几何 sim-to-real 差距，它们仍不适合用于基准评测。为应对这些挑战，我们提出 Wanderland，一个具备多传感器采集、可靠重建、精确几何与鲁棒视角合成的 real-to-sim 框架。借助该管线，我们构建了一个涵盖室内外城市场景的多样化数据集，并系统性地展示了纯图像管线如何难以扩展、几何质量如何影响新视角合成，以及上述所有因素如何对导航策略学习与评测可靠性产生不利影响。除作为具身导航的可信测试平台外，Wanderland 丰富的原始传感器数据还使得对 3D 重建与新视角合成模型的基准评测成为可能。我们的工作为开放世界具身智能的可复现研究奠定了新的基础。
英文原文摘要 1196 字符
Reproducible closed-loop evaluation remains a major bottleneck in Embodied AI such as visual navigation. A promising path forward is high-fidelity simulation that combines photorealistic sensor rendering with geometrically grounded interaction in complex, open-world urban environments. Although recent video-3DGS methods ease open-world scene capturing, they are still unsuitable for benchmarking due to large visual and geometric sim-to-real gaps. To address these challenges, we introduce Wanderland, a real-to-sim framework that features multi-sensor capture, reliable reconstruction, accurate geometry, and robust view synthesis. Using this pipeline, we curate a diverse dataset of indoor-outdoor urban scenes and systematically demonstrate how image-only pipelines scale poorly, how geometry quality impacts novel view synthesis, and how all of these adversely affect navigation policy learning and evaluation reliability. Beyond serving as a trusted testbed for embodied navigation, Wanderland's rich raw sensor data further allows benchmarking of 3D reconstruction and novel view synthesis models. Our work establishes a new foundation for reproducible research in open-world embodied AI.