Character image generation method guided by text based on generative adversarial network

Abstract

The invention discloses a character image generation method based on text guidance of a generative adversarial network, and belongs to the field of computer vision. The method specifically comprises the following steps: obtaining a figure image data set for training, and defining an algorithm target; acquiring attitude information of all images in the character image data set, and acquiring basicattitudes from all attitude information through a clustering algorithm; learning from characters to a predicted posture by using a posture predictor based on the generative adversarial network; predicting a corresponding figure posture from the text by using the posture predictor obtained by learning in the steps S2 to S3; using a character picture generator based on a generative adversarial network ito learn character picture generation conforming to text description, and meanwhile, using a multi-modal error to establish a mapping relation between a picture sub-region and a text. The character image generation method based on text guidance of the generative adversarial network has good application value in scenes of image generation, image editing, pedestrian re-identification and the like.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to a method for generating character images guided by texts based on generative confrontation networks. Background technique [0002] Text-guided person image generation is defined as the problem of simultaneously changing the pose and attributes (e.g., clothing color) of a person in a reference image to match the text description, according to the target text description. In recent years, in the fields of computer vision tasks such as specific image generation, image retrieval, and person re-identification, generative methods have played an important role in generating images with specified content, expanding data sets, and increasing the robustness of algorithms. There are two key points in this task: the first is how to predict the target pose of the character from the text, the target pose should be consistent with the text description, and serve as a guide for the transformation ...

AI Technical Summary

Problems solved by technology

Some previous methods considered the problem of changing the pose of the character, and some methods aimed at text-image generation, while fewer methods considered changing the pose and attributes of the character according to the description of the text

Images