Low-illumination image brightness enhancement and super-resolution method based on double-channel codec

Abstract

The invention relates to a low-illumination image brightness enhancement and super-resolution method based on a double-channel codec, and belongs to the technical field of computer vision images. The method comprises the steps of 1, performing feature extraction on a dark light image through an encoder sharing parameters to obtain a set of feature maps; 2, sending the feature map to a super-resolution decoder for decoding to obtain a super-resolution feature map; 3, pooling the feature map output by the encoder in the step 1 and the super-resolution feature map in the step 2 respectively to obtain two feature vectors, performing weighted fusion on the feature vectors by using an attention mechanism, and then sending the feature vectors to a low-illumination decoder for decoding; and finally, carrying out post-processing on the outputs of the two decoders to obtain a corresponding image after super-resolution. The invention is reasonable in design, low-illumination enhancement and image super-resolution tasks are combined for the defects of an existing low-illumination enhancement method, the visual effect of the reconstructed image is improved, and a good effect is achieved on the low-illumination enhancement and super-resolution comprehensive tasks on the whole.

Description

technical field [0001] The invention belongs to the technical field of computer vision images, in particular to a low-illuminance image brightness enhancement and super-resolution method based on a two-way codec. Background technique [0002] With the advancement of science and technology, mobile devices are becoming more and more popular, and image acquisition is becoming more and more convenient. However, in the process of image acquisition, limited by the camera equipment, shooting environment, and lighting conditions, dark-light images that are difficult to see are often captured, and the quality of dark-light images is usually low. For example, although the images captured by surveillance cameras have a higher resolution, they are actually of low quality and have serious noise, especially at night; Causes noise, blurring, and loss of detail in the image. These problems will not only affect the visual effect of the image, but also bring difficulties to subsequent appli...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the deficiencies of the prior art, aiming at the defects of the current low-illuminance enhancement method - the restored bright light image is not of high quality, lacks details and the subjective visual effect is poor, and skillfully combines low-illuminance enhancement and image super-resolution Combined with high-resolution tasks, a method for brightness enhancement and super-resolution of low-light images based on dual codecs is proposed with reasonable design, high-quality restored bright-light images and relatively light weight.

Images