Image blurring method and device, electronic device and readable storage medium

Abstract

The invention relates to an image blurring method and device, an electronic device and a readable storage medium, and the method comprises the steps: obtaining a target image; generating a depth imageof the target image based on a preset depth prediction model; wherein the depth prediction model is a convolutional neural network model obtained through training of training images of known depth maps under N scene types, and N is a natural number; and performing blurring processing on each pixel point in the target image according to the depth image to obtain a blurred image of the target image. The image blurring method solves the technical problems that an image blurring method in the prior art is high in requirement for hardware equipment, not ideal in blurring effect and the like. The technical effects of reducing the hardware equipment requirement of image blurring and improving the blurring effect are achieved.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to an image blurring method, device, electronic equipment and readable storage medium. Background technique [0002] When using a SLR camera to take pictures, the camera will realize the blur effect of objects with different depths of field according to the distance of the focus point. However, due to the limitations of hardware devices, electronic devices such as smart phones only have a depth of field in the photos taken, and the blur effect cannot be achieved, resulting in unrealistic images. [0003] In related technologies, the commonly used method is to predict the depth based on binocular vision and to blur the background based on segmentation. However, predicting the depth of each pixel in an image through binocular vision requires high hardware equipment, and the amount of calculation is complex and difficult to implement. Real-time application; whil...

AI Technical Summary

Problems solved by technology

However, these methods all need to manually design feature extractors, and the speed and accuracy of model prediction are difficult to guarantee.

It can be seen that the image blurring method in the related art has technical problems such as high requirements on hardware equipment and unsatisfactory blurring effect.

Images