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.
We present SynCity 3000, a framework for generating 3D scenes that are globally coherent while enabling fine-grained layout control. Building on the ability of current image-to-3D generators to produce complex 3D assets from a single image, we extend this capability to the scale of entire scenes by adapting the generator to be applicable as a convolutional operator. We achieve this by fine-tuning the model on scene-like data generated by a new synthetic data engine, which we propose to address the scarcity of 3D scene data for training. The convolutional generator is then applied to a dimetric image of the entire scene, generated from the user prompt, resulting in 3D scenes of arbitrary size and complexity. Across diverse prompts and layouts, SynCity 3000 produces large, coherent, and detailed scenes, addressing the shortcomings of prior approaches to 3D scene generation.
We present ABot-Earth 0.5, a generative 3D framework designed to synthesize vast, seamless 3D environments from ubiquitous, geospatially referenced satellite imagery. To achieve this, we propose a novel generative model formulated directly with the 3D Gaussian Splatting (3DGS) representation. The model is trained on a diverse corpus of existing real-world urban reconstructions, learning to generate realistic geometry and textures. At inference, it synthesizes novel 3D scenes conditioned solely on satellite imagery at a scalable rate of under 10 minutes per square kilometer, while demonstrating exceptional realism. The framework is designed for accessibility, with integrated hierarchical level-of-detail (LOD) structures that permit real-time, interactive visualization on web-based map engines. This high-fidelity simulation sandbox effectively mitigates the sim-to-real domain gap, enabling critical downstream Embodied AI applications like closed-loop UAV navigation. By providing an ultra-low-cost and high-efficiency solution, ABot-Earth 0.5 significantly lowers the technical and financial barriers to large-scale 3D reconstruction and empowers the future of global digital earth visualization.
Synthetic 3D scene generation is increasingly used as a data source for computer vision and embodied AI, but existing generators often optimize perceptual realism without reliably satisfying task-critical functional constraints. This mismatch limits the usefulness of synthetic data for downstream training, where accessibility, traversability, and spatial rule compliance are often essential. We present iARCS, an iterative agentic reinforcement learning framework that adapts a pretrained scene generator to naturallanguage task requirements. iARCS uses a two-phase strategy: universal-reward pretraining to improve physical plausibility and layout quality, followed by task-specific finetuning with LLM-generated reward programs that are iteratively refined from training feedback. Experiments show improved constraint fidelity on walkability, reachability, and clearance-focused tasks, effective task-specific constraint optimization, and competitive scene diversity. We further show that data generated by iARCS improves a base generator, supporting its value as a practical synthetic data generation tool rather than only a controllable scene editing method.