Real image generation method based on annotation images under unsupervised training and storage medium

Abstract

The invention discloses a real image generation method based on an annotation image under unsupervised training and a storage medium. The method comprises the following steps: inputting the annotationimage into a generator to generate three output images with different sizes; using a hierarchical visual perception discriminator to obtain six discrimination results; converting the discrimination result into adversarial loss by adopting an adversarial loss function; generating a blurred picture, and then calculating the confrontation loss of a discrimination result obtained by inputting the blurred picture into the hierarchical visual perception discriminator; performing adjacent pairwise grouping on the output images, inputting the output images into a VGG19 network, and then calculating the consistent loss of the images; inputting the output picture into three semantic segmentation networks ICNet which do not share parameters, and calculating return segmentation loss; collecting finallosses obtained by the four loss values to optimize the whole network, returning to the first step when the network is not converged, and taking the optimized generator as an image generation model when the network is converged; and generating a real image from the input annotation image by adopting an image generation model.

Description

technical field [0001] The invention relates to an image processing method, in particular to a method for generating a real image under unsupervised training based on an annotation map and a storage medium. Background technique [0002] With the development of deep neural networks, technologies such as image classification, image segmentation, and image object detection have been relatively mature and widely used. However, technologies related to image generation have not received widespread application support due to their poor performance in the face of high-quality and high-resolution requirements, and instability in model training and use. Among them, real image generation based on annotated images is one of the most functional directions. It uses the annotations given by users, which can be semantic annotations or hand-drawn approximate contours, to generate corresponding real images. Since the generated real image has realistic and rich content, and the generated sour...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned deficiencies in the prior art, the real image generation method and the storage medium provided by the present invention under unsupervised training based on the annotation map solve the problem that the existing algorithm does not work properly by combining multiple discriminant results outputted with multiple loss functions. stability problem

Images