Training method and device of neural network model for image processing

Abstract

The invention relates to a training method and device of a neural network model for image processing. The method comprises that video frames adjacent in time are obtained; the neural network model output intermediate images corresponding to the video frames respectively; change of the video frames in relatively earlier time and optical flow information of the video frames in relatively later timeare obtained; and image formed by changing the intermediate image, corresponding to the video frame in relatively earlier time, according to the optical flow information is obtained; time loss betweenthe intermediate image corresponding to the video frame in relatively later time and an image after change is obtained; characteristic loss between the intermediate image and a target characteristicimage is obtained; and the neural network model is adjusted according to the time loss and the characteristic loss, the step of obtaining the video frames adjacent in time is returned to, and trainingis not stopped until the neural network model satisfies a training ending condition. Thus, the neural network model obtained by training has a better video characteristic conversion effect.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a training method and device for a neural network model used for image processing. Background technique [0002] With the development of computer technology, in image processing technology, neural network models are usually used to convert image features, such as image color feature conversion, image light and shadow feature conversion, or image style feature conversion. Before performing feature conversion processing on an image through a neural network model, it is necessary to train a neural network model for image processing. [0003] The neural network model used for image processing trained by the traditional neural network model training method has a better effect on image feature conversion. However, when the neural network model is used to perform video feature conversion, a large amount of flicker noise will be introduced, resulting in a poor video feature conversion...

AI Technical Summary

Problems solved by technology

[0004] Based on this, it is necessary to provide a training method and device for a neural network model for image processing in view of the poor effect of traditional neural network models for image processing on video feature conversion

Images