Generative Pose Generation for Game Characters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques for generating realistic motion in electronic games are time-consuming and labor-intensive for game designers, often relying on manual adjustments of character models or motion capture methods that are limited in realism and flexibility.
Innovation Solution
The use of machine learning techniques, specifically generative models like autoencoders and variational autoencoders, to analyze and encode pose information from real-life persons, allowing for the rapid generation of realistic motion for in-game characters by learning a latent feature space that represents human motion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual adjustments of character models are used to generate realistic motion, then motion realism can be improved, but the time and labor required increase substantially
Solution Approach 1:
The patent uses motion capture technology to record real human movements and creates digital copies of these movements that can be applied to character models. This eliminates the need for manual adjustment of each character model while preserving realistic motion patterns captured from actual human performance.
Solution Approach 2:
The patent replaces the manual mechanical adjustment process with an automated system that uses motion capture data and computer algorithms to generate and apply motions to character models, significantly reducing the time and labor required while maintaining or improving motion realism.
2Manufacturing precision
If motion capture methods are used to generate character motion, then realism can be improved, but the complexity and cost of the system increase
Solution Approach 1:
The patent extracts only the essential motion data from complex motion capture sessions, separating the critical positional information from the full complexity of the capture process. This allows realistic motion to be achieved while reducing the overall system complexity by focusing on the most important data elements.
Solution Approach 2:
The patent transforms complex motion capture data into simplified parameter representations that can be efficiently stored and applied to character models. By changing the representation parameters from detailed raw data to essential motion parameters, the system complexity is reduced while preserving motion realism.
3Manufacturing precision
If detailed character models are created to increase realism, then the quality of the game experience improves, but the complexity and time required for model creation increase
Solution Approach 1:
The patent performs preliminary motion capture and character model preparation in advance, creating reusable motion libraries and standardized character models before game development begins. This preliminary action reduces the complexity of ongoing model creation and allows rapid deployment of realistic characters and motions during game production.
Data Source
AI summary
Systems and methods are provided for enhanced pose generation based on generative modeling. An example method includes accessing an autoencoder trained based on poses of real-world persons, each pose being defined based on location information associated with joints, with the autoencoder being trained to map an input pose to a feature encoding associated with a latent feature space. Information identifying, at least, a first pose and a second pose associated with a character configured for inclusion in an in-game world is obtained via user input, with each of the poses being defined based on location information associated with the joints and with the joints being included on a skeleton associated with the character. Feature encodings associated with the first pose and the second pose are generated based on the autoencoder. Output poses are generated based on transition information associated with the first pose and the second pose.