Video generation method, device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a video generation method, a device, electronic equipment and a storage medium, which are used for improving the resolution of an image in a video and effectively retaining feature details of the video. The method comprises the following steps: collecting an original video, and extracting attitude information and appearance information of a first object from the original video; determining attitude difference information between the attitude information of the first object and attitude information of a pre-collected second object, and determining feature information for representing appearance features of the first object based on the appearance information; generating multiple frames of initial images with first object appearance features and first object attitude features based on the feature information, migrating the attitude of the second object to each frame of initial image based on the attitude difference information, and generating multiple frames of target images with first object appearance features and second object attitude features; and forming a preset time sequence based on the posture change sequence of the migrated second object, and connecting the multiple frames of target images according to the preset time sequence to generate a target video.

Description

technical field [0001] The present disclosure relates to the field of video processing, and in particular to a video generation method, device, electronic equipment and storage medium. Background technique [0002] The intelligent generation of video content is used to simulate and reproduce the dynamic visual world, and has a wide range of applications in the fields of computer vision, robotics, and computer graphics. Using the learned video content intelligent generation model, users can generate realistic video content, and can perform advanced control and modification of video generated content in a conditionally constrained manner. [0003] Video generation solutions in the prior art mainly include intelligent generation of unconditional video content and intelligent generation of conditional video content. Among them, the intelligent generation of unconditional video content cannot control and modify the content of the generated video, and it is often difficult to obta...

AI Technical Summary

Problems solved by technology

However, related technologies tend to lose the feature details of the source domain characters when generating portraits based on pose information, and it is difficult to ensure the consistency of longer time series in the generated videos

[0004] To sum up, there are problems in the video generation scheme in the prior art that the resolution is not high enough, and it is easy to lose the details of character features.

Images