MULTIMODAL DISENTANGLEMENT FOR GENERATING VIRTUAL HUMAN AVATARS

Title:

MULTIMODAL DISENTANGLEMENT FOR GENERATING VIRTUAL HUMAN AVATARS

Document Type and Number:

WIPO Patent Application WO/2024/014819

Kind Code:

A1

Abstract:

Multimodal disentanglement can include generating a set of silhouette images corresponding to a human face, the generating undoing a correlation between an upper portion and a lower portion of the human face depicted by each silhouette image. A unimodal machine learning model can be trained with the set of silhouette images. As trained, the unimodal machine learning model can generate synthetic images of the human face. The synthetic images generated by the unimodal machine learning model once trained can be used to train a multimodal rendering network. The multimodal rendering network can be trained to generate a voice-animated digital human. Training the multimodal rendering network can be based on minimizing differences between the synthetic images and images generated by the multimodal rendering network.

More Like This:

JP2011028713	INFORMATION PROCESSING PROGRAM, INFORMATION PROCESSING APPARATUS AND OBJECT DISPLAYING METHOD
WO/2021/164620	MOTION DATA PROCESSING METHOD, APPARATUS AND DEVICE, AND STORAGE MEDIUM
JP7128473	Character display method

Inventors:

RAVICHANDRAN SIDDARTH (US)
DINEV DIMITAR PETKOV (US)
TEXLER ONDREJ (US)
GUPTA ANKUR (US)
PALAN JANVI CHETAN (US)
KANG HYUN JAE (US)
LIOT ANTHONY SYLVAIN JEAN-YVES (US)
SADI SAJID (US)

Application Number:

PCT/KR2023/009802

Publication Date:

January 18, 2024

Filing Date:

July 10, 2023

Export Citation:

Click for automatic bibliography generation Help

Assignee:

SAMSUNG ELECTRONICS CO LTD (KR)

International Classes:

G06T13/40; G06N20/00; G06T5/50; G06T13/20; G06V40/16; G10L21/10

Foreign References:

US20220129689A1	2022-04-28
US20200380246A1	2020-12-03
US20210166461A1	2021-06-03
US20190318194A1	2019-10-17

Other References:

TENG WENBIN; BAI CHONGYANG: "Unimodal Face Classification with Multimodal Training", 2021 16TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2021), IEEE, 15 December 2021 (2021-12-15), pages 1 - 5, XP034000389, DOI: 10.1109/FG52635.2021.9666965

Attorney, Agent or Firm:

KIM, Tae-hun et al. (KR)

Download PDF:

View/Download PDF PDF Help

Previous Patent: AIR TO GROUND COMMUNICATION

Next Patent: GRAPHENE-BASED SENSOR, MEASUREMENT DEVICE USING SAME, SPECIMEN MEASUREMENT METHOD, AND SPECIMEN ANAL...