Check patentability & draft patents in minutes with Patsnap Eureka AI!

Method and device for synthesizing video

A technology in video and video, applied in the computer field, can solve the problems of poor video authenticity, low quality of audio video, and mismatch between mouth shape and voice, and achieve the effect of ensuring quality, improving production efficiency and high matching degree.

Active Publication Date: 2020-05-29
BEIJING YUANLI WEILAI SCI & TECH CO LTD
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In existing video production, a voice and a silent video can be synthesized into a video with sound, but after the generated video with sound is played, the mouth shape does not correspond to the voice, and the mouth shape of the character does not match the voice very well. The authenticity of the synthesized video is poor, and the quality of the generated audio video is low, which cannot meet the needs of video production

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for synthesizing video
  • Method and device for synthesizing video
  • Method and device for synthesizing video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the application. However, the present application can be implemented in many other ways different from those described here, and those skilled in the art can make similar promotions without violating the connotation of the present application. Therefore, the present application is not limited by the specific implementation disclosed below.

[0061] Terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only, and are not intended to limit one or more embodiments of this specification. As used in one or more embodiments of this specification and the appended claims, the singular forms "a", "the", and "the" are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of the present spec...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a method and a device for synthesizing a video. The method comprises the following steps: obtaining a to-be-processed video matched with the original voice, intercepting the original voice to obtain a voice segment corresponding to an original image frame in a to-be-processed video, determining a target mouth shape key point coordinate corresponding to the voice segment, cutting off a mouth area in an original image frame corresponding to the voice segment to form a cut-off area, cutting off the mouth area in the original image frame corresponding to the voice segment toform a cut-off area; drawing a mouth-shaped contour in a cut-off area of an original image frame corresponding to the voice segment, generating the target image frames corresponding to the voice segments according to the original image frames corresponding to the voice segments and containing the mouth shape contours, synthesizing the target video according to the target image frames corresponding to the voice segments and the original voice. The matching degree of the mouth shape of a person in the target video and the original voice is high, and the quality of the synthesized target video is ensured.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a method and device for synthesizing video, a computing device, and a computer-readable storage medium. Background technique [0002] With the rapid development of computer technology, video production has also been widely used. Video production is to generate video through secondary encoding after non-linear editing of pictures, audio, video and other materials, and can synthesize multiple materials into video. [0003] In existing video production, a voice and a silent video can be synthesized into a video with sound, but after the generated video with sound is played, the mouth shape does not correspond to the voice, and the mouth shape of the character does not match the voice very well. The authenticity of the synthesized video is poor, and the quality of the generated audio video is low, which cannot meet the needs of video production. Contents of the inve...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): H04N5/265G06K9/00G06F16/783G06T7/11G06T7/181
CPCH04N5/265G06F16/7834G06F16/783G06T7/11G06T7/181G06T2207/10016G06V20/46
Inventor 程大治夏龙吴凡卓邦声高强马楠郭常圳
Owner BEIJING YUANLI WEILAI SCI & TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More