Combined low-illumination enhancement and deblurring method and device and storage medium

The invention belongs to the technical field of image processing and mode recognition, and particularly discloses a combined low-illumination enhancement and deblurring method and device based on Fourier diffusion prior and a storage medium. According to the combined low-illumination enhancement and deblurring method based on Fourier diffusion prior, the Fourier prior is ingeniously embedded into the sampling process of the diffusion model, the sampling process is guided through the image characteristics of the Fourier domain, any training data and degradation hypothesis are not needed, and the method is simple and easy to implement. The prior amplitude generated in the pre-training diffusion model and the iteratively optimized phase of the input image are utilized to gradually enhance the image brightness and definition on the premise of keeping the image content unchanged. 本发明属于图像处理和模式识别技术领域，具体公开了一种基于傅里叶扩散先验的联合低光照增强与去模糊方法、设备及存储介质。本发明基于傅里叶扩散先验的联合低光照增强与去模糊方法，将傅里叶先验巧妙地嵌入到扩散模型的采样过程中，通过傅里叶域的图像特性引导采样过程，无需任何训练数据和退