Three-dimensional digital human generation method and apparatus, electronic device and storage medium

By performing key point detection and feature vector generation on two-dimensional images and updating three-dimensional digital face data, the problem of low quality of two-dimensional images is solved, and more efficient and accurate three-dimensional digital life generation is achieved.

WO2024235064A1PCT designated stage expired Publication Date: 2024-11-21MOORE THREADS TECH CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/091541
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-15
Filing Date
2024-05-07
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

When generating three-dimensional digital humans, the two-dimensional image quality is uneven, resulting in low accuracy of three-dimensional digital human faces, which requires manual face pinching, which reduces the generation efficiency.

Method used

By performing key point detection on face images to be processed, face feature vectors are determined, initial digital face data is generated, and key point data is updated to improve the accuracy of three-dimensional digital faces, and the target three-dimensional numbers are generated using digital life generation software to process and generate target three-dimensional numbers. people.

Benefits of technology

It improves the accuracy and generation efficiency of three-dimensional digital faces, reduces manual intervention, and improves the accuracy and efficiency of the overall generation of three-dimensional digital faces.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024091541_21112024_PF_FP_ABST
    Figure CN2024091541_21112024_PF_FP_ABST
Patent Text Reader

Abstract

The present disclosure relates to a three-dimensional digital human generation method and apparatus, an electronic device and a storage medium. The method comprises: performing key point detection on a face image to be processed, to obtain first specific key point data; determining a first face feature vector corresponding to the face image to be processed; generating initial digital face data according to the first face feature vector, and updating the initial digital face data using the first specific key point data, to obtain three-dimensional digital face data; processing the three-dimensional digital face data using digital human generation software, to obtain a target three-dimensional digital human. Therefore, it is possible to improve the efficiency and accuracy of determining a target three-dimensional digital human.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Face model reconstruction method and device, equipment and storage medium

    CN114429518A

  • Three-dimensional model generation method and device

    CN114758090A

  • Virtual image generation method and device, equipment and storage medium

    CN115393486A

  • 3D face construction method

    CN115512039A

  • Three-dimensional digital human generation method and device, electronic equipment and storage medium

    CN116563432A