AirplaneGen: Skeleton-Guided Generation of Remote Sensing Images with Multi-Instance Airplanes

Zhu, Lingxuan; Ma, Yanze; Wu, Jiaji; Fan, Yanbo; Wang, Xiaobing; Tan, Mingzhou

doi:10.3390/rs18121940

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

AirplaneGen: Skeleton-Guided Generation of Remote Sensing Images with Multi-Instance Airplanes

by

Lingxuan Zhu

^1,2

,

Yanze Ma

³

,

Jiaji Wu

^1,*

,

Yanbo Fan

²,

Xiaobing Wang

² and

Mingzhou Tan

⁴

¹

The School of Electronic Engineering, Xidian University, Xi’an 710071, China

²

The National Key Laboratory of Scattering and Radiation, Shanghai 200438, China

³

The School of Computer Science and Engineering, The Southern University of Science and Technology, Shenzhen 518055, China

⁴

Emotion Machine Lab, Beijing 100101, China

^*

Author to whom correspondence should be addressed.

Remote Sens. 2026, 18(12), 1940; https://doi.org/10.3390/rs18121940

Submission received: 20 April 2026 / Revised: 4 June 2026 / Accepted: 9 June 2026 / Published: 11 June 2026

(This article belongs to the Special Issue Advances in Deep Learning and Machine Learning for Remote Sensing Image Analysis)

Download Versions Notes

Abstract

Generating realistic and controllable aerial images is important for building and evaluating remote sensing recognition systems, especially when real samples of rare aircraft types or dense airport layouts are limited. However, airplane synthesis remains challenging for generic generative models. Aircraft have rigid and symmetric structures, and airport scenes often contain many closely spaced instances; as a result, existing models tend to produce distorted wings and fuselages or merge adjacent airplanes into ambiguous shapes. To address these issues, we propose AirplaneGen, a skeleton-guided latent diffusion framework for multi-airplane remote sensing image generation. AirplaneGen represents each airplane with an editable eight-keypoint skeleton and uses skeleton-derived soft masks to separate instance-level refinement from background-context modeling during denoising. To support this task, we construct MARS20, a benchmark with 2778 high-resolution aerial scenes and 16,673 airplane instances annotated with skeletons, categories, and contextual descriptions. Experiments on MARS20 show that AirplaneGen improves image fidelity, geometric consistency, and instance separation over representative controllable generation methods.

Keywords: remote sensing; image generation; multi-instance; geometric constraint; diffusion model

Share and Cite

MDPI and ACS Style

Zhu, L.; Ma, Y.; Wu, J.; Fan, Y.; Wang, X.; Tan, M. AirplaneGen: Skeleton-Guided Generation of Remote Sensing Images with Multi-Instance Airplanes. Remote Sens. 2026, 18, 1940. https://doi.org/10.3390/rs18121940

AMA Style

Zhu L, Ma Y, Wu J, Fan Y, Wang X, Tan M. AirplaneGen: Skeleton-Guided Generation of Remote Sensing Images with Multi-Instance Airplanes. Remote Sensing. 2026; 18(12):1940. https://doi.org/10.3390/rs18121940

Chicago/Turabian Style

Zhu, Lingxuan, Yanze Ma, Jiaji Wu, Yanbo Fan, Xiaobing Wang, and Mingzhou Tan. 2026. "AirplaneGen: Skeleton-Guided Generation of Remote Sensing Images with Multi-Instance Airplanes" Remote Sensing 18, no. 12: 1940. https://doi.org/10.3390/rs18121940

APA Style

Zhu, L., Ma, Y., Wu, J., Fan, Y., Wang, X., & Tan, M. (2026). AirplaneGen: Skeleton-Guided Generation of Remote Sensing Images with Multi-Instance Airplanes. Remote Sensing, 18(12), 1940. https://doi.org/10.3390/rs18121940

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

AirplaneGen: Skeleton-Guided Generation of Remote Sensing Images with Multi-Instance Airplanes

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI