Training method of image enhancement model, image enhancement method and electronic equipment

Abstract

The invention relates to the technical field of image processing, in particular to a training method of an image enhancement model, an image enhancement method and electronic equipment, and the training method comprises the steps: obtaining a sample image pair which comprises a first quality sample image and a corresponding second quality sample image, the resolution of the first quality sample image is smaller than that of the second quality sample image; inputting the first quality sample image into an image enhancement model to obtain a predicted second quality image, the image enhancement model comprising at least one convolution unit and at least one residual unit, the residual unit comprising at least two data channels; and performing loss function calculation according to the second quality sample image and the predicted second quality image, updating parameters of the image enhancement model based on a calculation result, and determining a target image enhancement model. Under the condition of the same calculation amount, circulation of pixel information is increased, the depth of a network structure is reduced, and the efficiency of model training and subsequent execution is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a training method for an image enhancement model, an image enhancement method and electronic equipment. Background technique [0002] The image captured by the camera equipment in an environment with low light source illumination or strong backlight often has problems such as low brightness, high noise, and color cast. The main reason is that in a low-light environment, the number of photons entering the sensor is relatively small. If it is less, it will directly affect the image quality and subsequent related intelligent algorithm tasks, such as person recognition under night video surveillance, license plate recognition under backlight conditions, etc. Through the image enhancement technology, the noise in the image can be reduced while the brightness of the image is improved, the image information can be restored, the visual effect of the image can be improved, and th...

AI Technical Summary

Problems solved by technology

[0004] In view of this, an embodiment of the present invention provides a training method for an image enhancement model, an image enhancement method, and electronic equipment to solve the problem of low efficiency of image enhancement processing

Images