Animation sketch coloring method based on dynamic memory module and generative adversarial network

Abstract

The invention provides an animation sketch coloring method based on a dynamic memory module and a generative adversarial network, and belongs to the technical field of image processing. An image coloring task is completed by using a dynamic memory module for the first time, firstly, an animation sketch is input into a network, and a picture feature graph is obtained; information is dynamically read from the image tag by using a dynamic memory module, the image features and the image tag information are combined, and a generator and a discriminator are trained to generate a color image according with tag description. According to the invention, the dynamic memory module and the conditional generative adversarial network are utilized to achieve the task of generating the color picture from the animation sketch and the corresponding picture label, and the picture quality is improved by dynamically combining the label information and the image information; according to the invention, evaluation is carried out by using a real image data set, and the improvement on the most advanced baseline is observed.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for coloring animation sketches based on a dynamic memory module and a generative confrontation network. Background technique [0002] Image coloring technology is a very important research content in the field of image processing, involving algorithms in many aspects including computer vision, grayscale image processing, and color space transformation. Traditional image coloring methods are divided into image coloring methods based on local color and image coloring methods based on color transfer. The first method is also known as the brush-based coloring method. This algorithm requires the user to manually mark the part with a colored brush on the target image, and use this data as the basis for coloring to further colorize the entire image. Color expansion. The second method requires a color sample image similar to the picture to be colored, and...

AI Technical Summary

Problems solved by technology

[0004] At present, most of the problems in coloring pictures are as follows: (1) the color is wrong, and inappropriate colors are filled in the picture, such as green faces; (2) color penetration, the network often cannot distinguish between the foreground and Different instances in the background and pictures cause color bleeding between foreground and background and different instances; (3) Diversity of results, coloring pictures should have a variety of reasonable results, for example, a bird can be white, black, Yellow and other different colors

Images