Parametric 3D Body Modeling for Sparse Marker Soft-Tissue Capture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motion capture technologies using sparse marker sets fail to accurately estimate body shape and pose without the use of 3D scans, and do not effectively capture soft tissue motion, resulting in lifeless and unnatural animations.
Innovation Solution
A method and apparatus that utilize a parametric 3D body model to simultaneously estimate marker locations, body shape, and pose from sparse marker data, allowing for the capture of soft tissue motion by optimizing marker positions and body shape over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If sparse marker sets are used for motion capture, then the complexity of the system is reduced and ease of operation is improved, but measurement precision of body shape and pose estimation deteriorates
Solution Approach 1:
The patent introduces a parametric 3D body model as an intermediary between sparse markers and the target body shape/pose estimation. This model serves as a mediator that constrains the solution space and enables accurate reconstruction from limited marker data by incorporating prior knowledge of human body geometry and anatomy.
Solution Approach 2:
The patent transforms the estimation problem by changing parameters from direct marker-to-pose mapping to model-parameter optimization. By adjusting model parameters (shape coefficients, pose angles) to minimize the difference between predicted and observed marker positions, the system achieves precise estimation despite sparse input.
2Measurement precision
If 3D body scans are used to estimate body shape, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The parametric 3D body model acts as an intermediary that replaces the need for direct 3D scanning. Instead of using complex scanning hardware to capture body geometry, the system uses the parametric model to represent and estimate body shape from simpler marker data, thereby reducing device complexity while maintaining estimation accuracy.
Solution Approach 2:
The patent creates a simplified parametric copy of the actual body geometry that captures essential shape characteristics. This parametric representation serves as a manageable surrogate for the complex actual body surface, enabling accurate shape estimation without requiring complex scanning equipment.
3Device complexity
If traditional skeleton-based animation is used, then device complexity is reduced, but the realism of soft tissue motion deteriorates
Solution Approach 1:
The patent transitions from static skeleton-based animation to dynamic parametric model animation. The parametric body model can represent dynamic soft tissue deformations by adjusting shape parameters over time, capturing realistic soft tissue motion while maintaining relative simplicity through the use of predefined parametric forms rather than complex physical simulations.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for providing a three-dimensional body model which may be applied for an animation, based on a moving body, wherein the method comprises providing a parametric three-dimensional body model, which allows shape and pose variations; applying a standard set of body markers; optimizing the set of body markers by generating an additional set of body markers and applying the same for providing 3D coordinate marker signals for capturing shape and pose of the body and dynamics of soft tissue; and automatically providing an animation by processing the 3D coordinate marker signals in order to provide a personalized three-dimensional body model, based on estimated shape and an estimated pose of the body by means of predicted marker locations.