Electronic device, method, and non-transitory computer-readable storage medium for generating animation of character
By converting voice signals to a reference style and using multiple neural network models to generate animations, the challenge of generating realistic character animations is addressed, ensuring natural synchronization and high-quality facial expressions.
WO2026141708A1PCT designated stage Publication Date: 2026-07-02NCSOFT CORP
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- NCSOFT CORP
- Filing Date
- 2024-12-23
- Publication Date
- 2026-07-02
Smart Images
Figure KR2024020972_02072026_PF_FP_ABST
Abstract
An electronic device comprises: a memory storing instructions and including one or more storage media; and at least one processor including processing circuitry, wherein the instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to: obtain a first voice signal for utterance of a character; obtain, by providing the first voice signal to a first trained model, a second voice signal having a reference type that is different from a type of the first voice signal; generate, by providing the second voice signal to a second trained model, an animation representing a face of the character uttering the second voice signal; and output the first voice signal while displaying the animation.
Need to check novelty before this filing date? Find Prior Art