PID: Physics-Informed Diffusion Model for Infrared Image Generation

doi:10.1016/j.patcog.2025.111816

	PID: Physics-Informed Diffusion Model for Infrared Image Generation
	Mao, Fangyuan 1,2; Mei, Jilin 1; Lu, Shun 1,2; Liu, Fuyang 1,2; Chen, Liang 1; Zhao, Fangzhou 1; Hu, Yu 1,2
	2026
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
卷号	169 页码:14
摘要	Infrared imaging technology has gained notable attention for its reliable sensing ability in low visibility conditions, prompting numerous studies to convert the abundant RGB images to infrared images. However, most existing image translation methods treat infrared images as a stylistic variation, neglecting the fundamental principles of physics, which limits their practical application. To address these issues, we propose a Physics-Informed Diffusion (PID) model for translating RGB images to infrared images that adhere to physical laws. Our method leverages the iterative optimization of the diffusion model and incorporates strong physical constraints based on prior knowledge of infrared laws during training. This approach enhances the similarity between translated infrared images and the real infrared domain without increasing extra inference parameters. Experimental results demonstrate that PID significantly outperforms existing state-of-the-art methods. Our code is available at https://github.com/fangyuanmao/PID.
关键词	Physical constraints Diffusion model Infrared image generation
DOI	10.1016/j.patcog.2025.111816
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[U23B2034] ; National Natural Science Foundation of China[62203424] ; National Natural Science Foundation of China[62176250] ; Innovation Program of Institute of Computing Technology, Chinese Academy of Sciences[2024000112]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001513408300003
出版者	ELSEVIER SCI LTD
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42101
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Hu, Yu
作者单位	1.Chinese Acad Sci, Res Ctr Intelligent Comp Syst, Inst Comp Technol, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Mao, Fangyuan,Mei, Jilin,Lu, Shun,et al. PID: Physics-Informed Diffusion Model for Infrared Image Generation[J]. PATTERN RECOGNITION,2026,169:14.
APA	Mao, Fangyuan.,Mei, Jilin.,Lu, Shun.,Liu, Fuyang.,Chen, Liang.,...&Hu, Yu.(2026).PID: Physics-Informed Diffusion Model for Infrared Image Generation.PATTERN RECOGNITION,169,14.
MLA	Mao, Fangyuan,et al."PID: Physics-Informed Diffusion Model for Infrared Image Generation".PATTERN RECOGNITION 169(2026):14.