Extremely low illumination image enhancement method based on generative adversarial network

Abstract

The invention relates to an extremely low illumination image enhancement method based on a generative adversarial network. The method comprises the following steps of: obtaining original image data ofa shot image through an imaging sensor of shooting equipment, and preprocessing the original image data; wherein the original image data is Bayer array data Bayer array s; inputting the preprocessedimage data into a generative adversarial network; wherein the generative adversarial network comprises a generation model and a discrimination model, the generation model is used for image enhancement, and the discrimination model is used for training learning, so that the generated image is enhanced to an optimal image; and processing an output result of the generative adversarial network, and storing the output result as an image. According to the invention, under-exposure and darker images shot in an extremely low illumination environment or a night environment can be enhanced into clear and bright pictures through the method provided by the invention.

Description

technical field [0001] The invention relates to the fields of computer vision, deep learning, and computational photography. Background technique [0002] With the rapid development of society, people have more and more demands for automatic processing of images. With the rapid development of deep learning, more and more computer vision tasks have been solved well, but there are still many unsatisfactory situations when people take pictures in extremely low-light environments or at night. Especially when using a mobile phone or a poor device, when taking photos in an environment with extremely poor lighting conditions, the imaging quality of the device often disappoints us. Therefore, it is very meaningful to study image enhancement technology in extremely low-light environments or at night, which can greatly reduce the cost of many night-time surveillance devices, improve their capabilities, and at the same time enhance the imaging capabilities of smartphones. [0003] At...

AI Technical Summary

Problems solved by technology

[0003] At present, most image enhancement technologies in extremely low-light environments or at night use traditional methods, such as histogram equalization, inter-frame fusion, retinex, etc. These methods have achieved good results in many aspects, but There are still deficiencies, for example: for the enhanced image, a lot of noise will be introduced, and the restoration of the image is not realistic enough, etc.

Images