AeroScene: Progressive Scene Synthesis for Aerial Robotics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vu, Nghia, Do, Tuong, Tran, Dzung, Nguyen, Binh X., Nguyen, Hoan, Tjiputra, Erman, Tran, Quang D., Nguyen, Hai-Nguyen, Nguyen, Anh
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914484659945472
author Vu, Nghia
Do, Tuong
Tran, Dzung
Nguyen, Binh X.
Nguyen, Hoan
Tjiputra, Erman
Tran, Quang D.
Nguyen, Hai-Nguyen
Nguyen, Anh
author_facet Vu, Nghia
Do, Tuong
Tran, Dzung
Nguyen, Binh X.
Nguyen, Hoan
Tjiputra, Erman
Tran, Quang D.
Nguyen, Hai-Nguyen
Nguyen, Anh
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2603_23224
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AeroScene: Progressive Scene Synthesis for Aerial Robotics
Vu, Nghia
Do, Tuong
Tran, Dzung
Nguyen, Binh X.
Nguyen, Hoan
Tjiputra, Erman
Tran, Quang D.
Nguyen, Hai-Nguyen
Nguyen, Anh
Robotics
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/
title AeroScene: Progressive Scene Synthesis for Aerial Robotics
topic Robotics
url https://arxiv.org/abs/2603.23224