A virtual image generation method, device, equipment and medium

Abstract

Embodiments of the present disclosure relate to a method, device, device, and medium for generating an avatar, wherein the method includes: acquiring a target image in response to user input; generating an avatar corresponding to the target image through a first generator; wherein, the first generating The detector is trained based on the first sample image set and the second sample image set generated by the 3D model. The disclosure uses the first generator to effectively simplify the generation method of the avatar, improve the generation efficiency, and can generate the avatar corresponding to the target image one-to-one, making the avatar more diverse; at the same time, the first generator is easy to deploy in In various production environments, the performance requirements for hardware devices are reduced.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, and in particular to a method, device, equipment and medium for generating a virtual image. Background technique [0002] Three-dimensional avatars with cartoon and animation styles are widely used in virtual anchors, e-commerce, news media and other scenarios, and have received more and more attention and love from users. At present, the three-dimensional virtual image is generally rendered and generated by means of CG (Computer Graphics, computer graphics). However, the virtual image generated by CG method is single and lacks individuation. If a variety of virtual images are to be realized, it needs to be modified from modeling, which takes a long time to produce and high labor costs; Graphics card) has extremely high requirements. In terms of rendering visual effects such as image fidelity and light and shadow complexity, it is difficult to generate a satisfactory vir...

AI Technical Summary

Problems solved by technology

However, the virtual image generated by CG method is single and lacks individuation. If you want to realize a variety of virtual images, you need to modify it from modeling, which takes a long time to make and high labor costs; Graphics card) has extremely high requirements. In terms of rendering visual effects such as image fidelity and light and shadow complexity, it is difficult to generate satisfactory virtual images by using hardware devices with limited performance (such as mobile phones).

Images