AeroGen

[!WARNING] we do not have a full checkpoint conversion validation, if you encounter pipeline loading failure and unsidered output, please contact me via [email protected]

BiliSakura/AeroGen

Aerial image generation conditioned on bounding boxes (horizontal or rotated) and object categories. AeroGen is the first model to simultaneously support horizontal and rotated bounding box condition generation for remote sensing imagery.

Converted to diffusers format. Self-contained — no external code repo needed; all required code is bundled.

Model Details

• Model type: Latent diffusion with UNet + VAE + CLIP text encoder + RBoxEncoder (condition encoder)
• Conditioning: Bounding boxes (8 coords for rotated, 4 for axis-aligned), category CLIP embeddings, spatial masks
• Scheduler: DDIMScheduler, 1000 steps, scaled_linear
• Output: 512×512 RGB aerial images
• License: Apache 2.0

Repository Structure

Inference

Dependencies: pip install diffusers transformers torch einops safetensors pyyaml

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    "BiliSakura/AeroGen",
    custom_pipeline="pipeline.py",
    trust_remote_code=True,
)
pipe = pipe.to("cuda")

Conditioning Format

For layout preparation and DIOR-R format, see the original AeroGen repo.

Model Sources

• Source: Sonetto702/AeroGen
• Paper: AeroGen: Enhancing Remote Sensing Object Detection with Diffusion-Driven Data Generation
• Original repo: Sonettoo/AeroGen
• Conversion: Checkpoint converted to diffusers format (self-contained, no external repo)

Citation

@inproceedings{tangAeroGenEnhancingRemote2025,
  title = {{{AeroGen}}: {{Enhancing Remote Sensing Object Detection}} with {{Diffusion-Driven Data Generation}}},
  shorttitle = {{{AeroGen}}},
  booktitle = {{{CVPR}}},
  author = {Tang, Datao and Cao, Xiangyong and Wu, Xuan and Li, Jialin and Yao, Jing and Bai, Xueru and Jiang, Dongsheng and Li, Yin and Meng, Deyu},
  year = 2025,
  pages = {3614--3624},
  urldate = {2025-11-20}
}