PID：用于红外图像生成的物理启发扩散模型
PID: Physics-Informed Diffusion Model for Infrared Image Generation
AI总结：
针对现有RGB转红外图像方法忽略物理规律的问题，提出物理启发扩散模型PID，通过在扩散模型训练中加入红外物理约束，在不增加训练参数的情况下显著提升转换效果，性能优于现有最优方法。
摘要：
红外成像技术凭借在低能见度条件下可靠的感知能力受到广泛关注，这推动了许多将丰富的RGB图像转换为红外图像的研究。然而，现有大多数图像转换方法将红外图像视为一种风格变体，忽略了其背后的物理规律，这限制了它们的实际应用。为解决这些问题，我们提出了物理启发扩散（Physics-Informed Diffusion，PID）模型，用于将RGB图像转换为符合物理规律的红外图像。我们的方法利用扩散模型的迭代优化特性，并在训练过程中结合基于红外规律先验知识的强物理约束。该方法在不增加额外训练参数的情况下，提升了转换后红外图像与真实红外域的相似度。实验结果表明，PID显著优于现有的最优方法。我们的代码可在https://github.com/fangyuanmao/PID获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
