A method and device for processing persona data

An image and data technology, applied in the fields of computer vision, deep learning, and artificial intelligence, can solve problems such as increasing the cost of virtual human image production, and achieve the effect of enriching dynamic images and improving clarity.
CN112017140APending Publication Date: 2020-12-01BEIJING BAIDU NETCOM SCI & TECH CO LTD
2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
BEIJING BAIDU NETCOM SCI & TECH CO LTD
Publication Date
2020-12-01

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a method and device for processing figure data, and relates to the technical field of computer vision and deep learning. The specific implementation mode comprises the steps ofobtaining a figure video of a first figure to serve as first data, obtaining a figure video of a second figure to serve as second data, and the figure video of the first figure has multiple dynamic images; replacing the head portrait extracted from the first data with the head portrait extracted from the second data; replacing the face extracted from the first data with the face extracted from the second data; and replacing the face in the replaced head portrait with the replaced face to obtain a target head portrait. Through the head changing operation, the head-changed head portrait has different characteristics of different head portraits. And moreover, the first character with rich dynamic images is combined, so that the problem of insufficient dynamic image richness of the second character can be solved. In addition, the definition of the human face in the replaced head portrait can be effectively improved for the human face replacement operation.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present application relates to the technical field of artificial intelligence, specifically to the technical field of computer vision and deep learning, and especially to a method and device for processing character image data. Background technique

[0002] With the development of virtual image generation technology, digital virtual human has shown great application potential in many industries. Digital Avatar is a multi-modal human video generation task that can drive avatars through speech or text.

[0003] The modeling of digital virtual humans often requires recording a large amount of data in a specific environment. Every time a new image is modeled, the model needs to be invited to a professional studio in person, and a professional director is required to guide and complete some specific tasks. performance, which undoubtedly increases the cost of virtual human image production. Contents of the invention

[0004] Provided are a method, de...

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