Three-dimensional cartoon image processing method and device, computer device and storage medium
By acquiring and driving the removal of facial expressions in real time, the problem of low matching degree between 3D cartoon images and real facial expressions is solved by using facial feature prediction networks and machine learning technology, thus realizing the synchronous change of 3D cartoon images and user facial expressions.
CN115546361BActive Publication Date: 2026-07-10TENCENT TECHNOLOGY (SHENZHEN) CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TENCENT TECHNOLOGY (SHENZHEN) CO LTD
- Filing Date
- 2021-06-30
- Publication Date
- 2026-07-10
AI Technical Summary
Technical Problem
The existing technology does not produce 3D cartoon images that match the expressions of real human faces very well, and cannot accurately simulate the changes in facial expressions.
Method used
By acquiring a basic 3D cartoon image with removed facial expressions and then tracking the user's facial expressions in real time within the camera's field of view, a 3D cartoon image synchronized with the user's facial expressions is generated using facial feature prediction networks and machine learning techniques.
Benefits of technology
It achieves a high degree of matching and synchronous changes between 3D cartoon characters and real human facial expressions, generating cartoon characters that match the user's real-time expressions.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN115546361B_ABST
Abstract
The application relates to a three-dimensional cartoon figure processing method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining a basic three-dimensional cartoon figure after removing an expression; when a target user is in a camera field of view and the target user has an expression, displaying a three-dimensional cartoon figure obtained by changing the basic three-dimensional cartoon figure; the expression of the three-dimensional cartoon figure matches the expression of the target user; when the target user has an expression change in the camera field of view, following the expression change of the target user, displaying a three-dimensional cartoon figure obtained by changing the basic three-dimensional cartoon figure, which keeps synchronization with the expression of the target user. The method can accurately generate a three-dimensional cartoon figure with high expression matching degree of a real face.
Need to check novelty before this filing date? Find Prior Art