Soft computing-driven infrared UAV image synthesis from visible light: Leveraging multi-scale adaptation and physical consistency for real-world anti-UAV applications

Xu Bowei

doi:10.1016/j.asoc.2026.116139

Soft computing-driven infrared UAV image synthesis from visible light: Leveraging multi-scale adaptation and physical consistency for real-world anti-UAV applications

2026-08-04

0

PRE

AI

X

Xu Bowei

Z

Zhong Jianlin *

Z

Zhuo Changfei

J

Ji Wenxuan

Y

Yang Huaxin

L

Luo Xiang

D

Ding Zhixing

DOI：10.1016/j.asoc.2026.116139

Original

Original request for help

Save

Abstract

En 中文

• Soft computing multi-scale model generates realistic infrared UAV images with consistency. • Introduces temperature-emissivity decomposition for physical realism in infrared images. • Multi-scale enhancement improves detail and edge preservation in complex environments. • Deformable multi-scale discriminator enhances geometric adaptation and infrared image fidelity. • Outperforms baselines and enhances infrared dataset generation for anti-UAV detection.

Soft computing-driven infrared UAV image synthesis from visible light: Leveraging multi-scale adaptation and physical consistency for real-world anti-UAV applications

Abstract

Journal

Organization

Cited Papers

Citing Papers