PID: Physics-Informed Diffusion Model for Infrared Image Generation
This addresses the need for reliable infrared image generation in low-visibility conditions, though it appears incremental as it builds on existing diffusion models with added physical constraints.
The paper tackles the problem of generating realistic infrared images from RGB images by incorporating physical laws into a diffusion model, resulting in significant performance improvements over existing state-of-the-art methods.
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.