Image conversion system and method, storage medium and electronic equipment

Abstract

The embodiment of the invention discloses an image transformation system and method, a storage medium and electronic equipment. The image transformation system mainly comprises an image acquisition assembly used for acquiring a first image containing a target object and a second image containing a reference object; the image transformation component is used for inputting the first image and the second image into an image transformation model and obtaining a target image obtained by the image transformation model; wherein the image transformation model adopts a deformable attention mechanism to predict features of a target object and a reference object in a target image, the predicted features are utilized to further obtain the target image, and a partial region of the reference object in the target object is transformed into the target object. According to the invention, the transformation effect of image transformation can be effectively improved.

Description

[0001] This application claims the priority of the Chinese patent application with the application number of 202210707933.9 and the application title of "image transformation system, method, storage medium and electronic device" filed with the China Patent Office on June 22, 2022, the entire contents of which are incorporated by reference in this application. technical field [0002] The present application relates to the technical field of artificial intelligence, and in particular, to an image transformation system, method, storage medium and electronic device. Background technique [0003] With the continuous popularization and development of the Internet and e-commerce, online shopping for clothing has become one of the common consumption methods for people. In e-commerce websites, pictures of models wearing clothing can well show the appearance and style of clothing, which is now an indispensable part of the clothing field. However, shooting different styles of clothin...

AI Technical Summary

Problems solved by technology

However, shooting different styles of clothing displays requires models wearing different styles of clothing to be photographed separately, which is expensive, and post-processing also brings additional time and cost consumption

[0004] With the rapid development of deep learning, a method of automatically generating fitting images based on clothing images and model images has emerged. The essence is to transform the model image into the image of the model wearing the clothing in the clothing image, but the transformation effect still needs to be improved.

Images