用分层扩散模型自动生成逼真航拍场景，提升无人机仿真效率。
AeroScene: Progressive Scene Synthesis for Aerial Robotics
- 分层扩散架构结合全局布局与局部细节推理
- 生成超1000个物理可运行的高保真3D场景
- 适合需要真实仿真环境的无人机导航研究
生成模型在多个领域已展现巨大潜力，但在机器人场景合成方面仍处于探索阶段，尤其在无人机模拟器中，环境构建仍高度依赖人工，耗时且难扩展。本文提出AeroScene，一种用于渐进式3D场景合成的分层扩散模型。该方法通过层次感知标记化与多分支特征提取，同时兼顾整体布局与局部细节，确保场景的物理合理性与语义一致性，特别适用于无人机导航、着陆和停靠等任务。我们在新收集的数据集和公开基准上进行了大量实验，结果表明AeroScene显著优于现有方法。此外，我们利用AeroScene生成了超过1000个可直接集成至NVIDIA Isaac Sim的物理可用、高保真3D场景。最后，我们在下游无人机导航任务中验证了生成环境的有效性。代码与数据集已公开于 aioz-ai.github.io/AeroScene/
原文摘要 · Abstract (English)
Generative models have shown substantial impact across multiple domains, their potential for scene synthesis remains underexplored in robotics. This gap is more evident in drone simulators, where simulation environments still rely heavily on manual efforts, which are time-consuming to create and difficult to scale. In this work, we introduce AeroScene, a hierarchical diffusion model for progressive 3D scene synthesis. Our approach leverages hierarchy-aware tokenization and multi-branch feature extraction to reason across both global layouts and local details, ensuring physical plausibility and semantic consistency. This makes AeroScene particularly suited for generating realistic scenes for aerial robotics tasks such as navigation, landing, and perching. We demonstrate its effectiveness through extensive experiments on our newly collected dataset and a public benchmark, showing that AeroScene significantly outperforms prior methods. Furthermore, we use AeroScene to generate a large-scale dataset of over 1,000 physics-ready, high fidelity 3D scenes that can be directly integrated into NVIDIA Isaac Sim. Finally, we illustrate the utility of these generated environments on downstream drone navigation tasks. Our code and dataset are publicly available at aioz-ai.github.io/AeroScene/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。