Organizations: AIOZ Ltd., Singapore · University of Liverpool, UK · National Tsing Hua University, Taiwan · RMIT University, Vietnam Campus · University of Information Technology, VNUHCM, Vietnam.
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/
Figures & tables
Simulator
Physics
Diversity
Scalability
Indoor
Outdoor
Multi-scale
RotorS [ 7 ]
✓
Low
Limited
✓
✗
✗
AirSim [ 8 ]
✓
Medium
Limited
✓
✓
✗
OmniDrones [ 13 ]
✓
Medium
High
✓
Partial
✗
QuadSwarm [ 14 ]
✓
Low
High
✓
✗
✗
VisFly [ 15 ]
✓
High
Medium
Partial
✓
✗
IAP [ 16 ]
✓
High
Medium
✓
Partial
✗
TABLE I: Comparison of drone simulators.
Fig. 2: An overview of our AeroScene method.
Method
FID ↓
KID ↓
CR (%) ↓
CFC ↓
SP ↓
Our Dataset
ATISS [ 22 ]
45.2
0.032
12.5
0.21
3.8
Diffusion-SDF [ 58 ]
38.7
0.028
10.1
0.18
3.5
DiffuScene [ 24 ]
32.4
0.025
8.3
0.15
3.2
PhyScene [ 38 ]
29.8
0.023
7.1
0.13
3.0
Ours
27.3
0.021
6.2
0.12
2.7
TABLE II: Quantitative results on scene synthesis.
Fig. 3: Outdoor scene generation visual comparison. The red circle shows the collision or incorrect position.
Fig. 4: Indoor scene generation visual comparison. The red circle shows the collision or incorrect position.
Configuration
FID ↓
CR (%) ↓
CFC ↓
SP ↓
Ours (full)
27.3
6.2
0.12
2.7
w/o Collision
32.1
8.7
0.13
2.8
w/o C2F
30.5
6.5
0.15
2.9
w/o Semantic
31.8
6.4
0.13
3.5
w/o All Guidance
35.4
9.2
0.17
3.9
TABLE III: Ablation on guidance objectives.
Fig. 5: The generation sequence of objects in our method.
Criteria
Train
Test
Total
#Scenes
812
204
1016
#Objects
122,356
37,654
160,010
Avg. objects/scene
149
152
149
Avg. objs / coarse-scale level
35
32
34
Avg. objs / fine-scale level
111
114
112
Avg. Landing Areas for Drones
55
53
54
TABLE IV: Statistics of our dataset.
Metric
Value
Drone Platforms
2
Trajectories per Scene
300
Overall Success Rate
91%
TABLE V: Evaluation summary of navigation and interaction tasks on the AeroScene dataset.
Fig. 6: Generated navigation and interaction trajectories for the example mission: landing on the red roof of the Weefit building. Green lines represent feasible navigation and interaction trajectories, and red lines denote failed attempts. Sampled point clouds are displayed within the blue box, with red dots indicating failure landing points.