Title:
ANIMATION GENERATION METHOD AND APPARATUS, COMPUTER DEVICE, STORAGE MEDIUM, COMPUTER PROGRAM, AND COMPUTER PROGRAM PRODUCT
Document Type and Number:
WIPO Patent Application WO/2023/071801
Kind Code:
A1
Abstract:
An animation generation method, comprising: acquiring a target video comprising a target object (S101); extracting human body features respectively corresponding to at least two video frames in the target video (S102); on the basis of the human body features respectively corresponding to the at least two video frames in the target video and a neural network trained in an a priori space, determining a target a priori motion feature that matches with a target motion carried out by the target object in the target video, wherein the target a priori motion feature corresponding to the target motion is fused with at least two sample motion data frames for describing the target motion, and the a priori space comprises a priori motion features respectively corresponding to at least two motions (S103); and generating, on the basis of the target a priori motion feature, a three-dimensional motion animation that comprises a virtual object carrying out the target motion carried out by the target object (S1014).
Inventors:
XU JIACHEN (CN)
WANG MIN (CN)
LIU WENTAO (CN)
QIAN CHEN (CN)
MA LIZHUANG (CN)
WANG MIN (CN)
LIU WENTAO (CN)
QIAN CHEN (CN)
MA LIZHUANG (CN)
Application Number:
PCT/CN2022/124879
Publication Date:
May 04, 2023
Filing Date:
October 12, 2022
Export Citation:
Assignee:
SHANGHAI SENSETIME INTELLIGENT TECH CO LTD (CN)
International Classes:
G06T13/40
Foreign References:
| CN113920232A | 2022-01-11 | |||
| US20040051783A1 | 2004-03-18 | |||
| CN113556600A | 2021-10-26 | |||
| CN113192109A | 2021-07-30 |
Other References:
LEE, SEONG-WHAN ; LI, STAN Z: "SAT 2015 18th International Conference, Austin, TX, USA, September 24-27, 2015", vol. 11209 Chap.17, 6 October 2018, SPRINGER , Berlin, Heidelberg , ISBN: 3540745491, article YAN XINCHEN; RASTOGI AKASH; VILLEGAS RUBEN; SUNKAVALLI KALYAN; SHECHTMAN ELI; HADAP SUNIL; YUMER ERSIN; LEE HONGLAK: "MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics", pages: 276 - 293, XP047488909, 032548, DOI: 10.1007/978-3-030-01228-1_17
Attorney, Agent or Firm:
CHINA PAT INTELLECTUAL PROPERTY OFFICE (CN)
Download PDF:
Previous Patent: METHOD AND APPARATUS FOR INTERNET OF THINGS PAYMENT BASED ON SMART CONTRACT
Next Patent: SATELLITE COMMUNICATION METHOD AND APPARATUS
Next Patent: SATELLITE COMMUNICATION METHOD AND APPARATUS