PID: Physics-Informed Diffusion Model for Infrared Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mao, Fangyuan, Mei, Jilin, Lu, Shun, Liu, Fuyang, Chen, Liang, Zhao, Fangzhou, Hu, Yu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915626193256448
author Mao, Fangyuan
Mei, Jilin
Lu, Shun
Liu, Fuyang
Chen, Liang
Zhao, Fangzhou
Hu, Yu
author_facet Mao, Fangyuan
Mei, Jilin
Lu, Shun
Liu, Fuyang
Chen, Liang
Zhao, Fangzhou
Hu, Yu
contents Infrared imaging technology has gained significant attention for its reliable sensing ability in low visibility conditions, prompting many 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 underlying physical laws, 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 training parameters. Experimental results demonstrate that PID significantly outperforms existing state-of-the-art methods. Our code is available at https://github.com/fangyuanmao/PID.
format Preprint
id arxiv_https___arxiv_org_abs_2407_09299
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PID: Physics-Informed Diffusion Model for Infrared Image Generation
Mao, Fangyuan
Mei, Jilin
Lu, Shun
Liu, Fuyang
Chen, Liang
Zhao, Fangzhou
Hu, Yu
Computer Vision and Pattern Recognition
Infrared imaging technology has gained significant attention for its reliable sensing ability in low visibility conditions, prompting many 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 underlying physical laws, 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 training parameters. Experimental results demonstrate that PID significantly outperforms existing state-of-the-art methods. Our code is available at https://github.com/fangyuanmao/PID.
title PID: Physics-Informed Diffusion Model for Infrared Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.09299