Title:
GENERATIVE ADVERSARIAL NETWORK-BASED FACIAL EXPRESSION GENERATION METHOD
Document Type and Number:
WIPO Patent Application WO/2022/205416
Kind Code:
A1
Abstract:
Disclosed is a generative adversarial network-based facial expression generation method. The method comprises: constructing a deep learning network model, which comprises a recurrent neural network, a generator, an image discriminator, a first video discriminator, and a second video discriminator, wherein the recurrent neural network produces a time-related movement vector for an input image, the generator takes the movement vector and the input image as input, and outputs a corresponding video frame, the image discriminator is used for determining the authenticity of each video frame, the first video discriminator determines the authenticity of a video and performs classification, and the second video discriminator controls the realness and smoothness of a generated video change; training the deep learning network model using sample images containing different expression types as input; and using the trained generator to generate a facial video in real time. The present invention is able to generate an expression while retaining a facial feature, a generated video preserves continuity and realness, and same has a generalization ability for different human faces.
Inventors:
WANG RUI (CN)
SHI FAN (CN)
QU QIANG (CN)
JIANG QINGSHAN (CN)
SHI FAN (CN)
QU QIANG (CN)
JIANG QINGSHAN (CN)
Application Number:
PCT/CN2021/085263
Publication Date:
October 06, 2022
Filing Date:
April 02, 2021
Export Citation:
Assignee:
SHENZHEN INST ADV TECH (CN)
International Classes:
G06K9/00
Foreign References:
| US20180288431A1 | 2018-10-04 | |||
| CN110210429A | 2019-09-06 | |||
| CN109726654A | 2019-05-07 | |||
| CN111028305A | 2020-04-17 | |||
| CN108268845A | 2018-07-10 | |||
| US10671838B1 | 2020-06-02 |
Other References:
TULYAKOV SERGEY; LIU MING-YU; YANG XIAODONG; KAUTZ JAN: "MoCoGAN: Decomposing Motion and Content for Video Generation", 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, IEEE, 18 June 2018 (2018-06-18), pages 1526 - 1535, XP033476116, DOI: 10.1109/CVPR.2018.00165
Attorney, Agent or Firm:
BEIJING CHENGHUI LAW FIRM (CN)
Download PDF:
Previous Patent: TIMING ADVANCE IN LAYER 1/LAYER 2 INTER-CELL MOBILITY
Next Patent: RADIATION CURABLE (METH) ACRYLIC ADHESIVE COMPOSITION
Next Patent: RADIATION CURABLE (METH) ACRYLIC ADHESIVE COMPOSITION