Avatar Motion Style Transformation via Autoencoder Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional emoji and graphics in electronic messaging lack diversity and fail to represent individual users' personalities or distinguish between interactions, making conversations visually indistinguishable.
Innovation Solution
A system that uses an autoencoder neural network to transform avatar motion styles in real-time, allowing users to select and customize avatars based on their sentiment, enabling non-linear style translation on limited resource devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional emoji and graphics are used in electronic messaging, then the implementation is simple and device-compatible, but the visual diversity and ability to represent individual user personalities is lacking
Solution Approach 1:
The system performs preliminary actions by pre-training the neural network model offline to learn style transformations between different avatar appearances. This pre-computed knowledge is then applied in real-time messaging without requiring complex runtime processing, thus achieving visual diversity while maintaining device compatibility.
Solution Approach 2:
The patent introduces an intermediary neural network model that acts as a mediator between the user's selected avatar and the desired style transformation. This intermediary component handles the complex transformation logic, allowing the messaging system itself to remain simple while achieving sophisticated visual personalization.
2Adaptability or versatility
If neural network models are used for real-time style transformation, then the visual personalization and sentiment representation is enhanced, but the processing time and computational resources increase
Solution Approach 1:
The neural network model is pre-trained offline to learn the complex mappings between different avatar styles and sentiment expressions. This preliminary training phase separates the computationally intensive learning process from the real-time application, allowing fast inference during actual messaging without sacrificing transformation quality.
Solution Approach 2:
The system applies style transformation selectively based on user needs and message context rather than transforming every message. This partial application approach reduces overall processing time while maintaining the enhanced personalization capability when actually needed.
3Adaptability or versatility
If comprehensive avatar customization options are provided, then the user expression capability is improved, but the device resource requirements and system complexity increase
Solution Approach 1:
The patent extracts the complex customization logic into a separate neural network model that can be independently trained and applied. This extraction allows the core messaging system to remain lightweight while providing comprehensive customization capabilities through the dedicated transformation model.
Solution Approach 2:
The system achieves comprehensive customization by transforming a limited set of base avatar parameters through learned transformations rather than requiring all possible customization options to be explicitly implemented. This parameter-based approach reduces data requirements while maintaining versatility.
Data Source
AI summary
Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program and a method for transforming a motion style of an avatar from a first style to a second style. The program and method include: retrieving, by a processor from a storage device, an avatar depicting motion in a first style; receiving user input selecting a second style; obtaining, based on the user input, a trained machine learning model that performs a non-linear transformation of motion from the first style to the second style; and applying the obtained trained machine learning model to the retrieved avatar to transform the avatar from depicting motion in the first style to depicting motion in the second style.