Personalized 3D Body Models from 2D Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current three-dimensional modeling of the human body requires expensive or large sensors, and there is a need for methods to accurately determine body fat percentage using two-dimensional images.
Innovation Solution
A system and method that uses a portable device with a 2D camera to collect images from different angles, which are then processed using neural networks to generate a personalized three-dimensional body model, allowing users to view and interact with their body measurements and adjust them to predict different body compositions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional three-dimensional body modeling methods are used, then measurement accuracy is improved, but device cost and complexity increase
Solution Approach 1:
The patent creates a three-dimensional digital copy (virtual model) of the human body from two-dimensional images. Instead of using complex physical sensors to directly measure body composition, the system captures 2D images, processes them through neural networks to generate a 3D virtual model, and then determines body fat from this digital representation. This copying approach replaces expensive specialized sensors with standard 2D imaging equipment.
Solution Approach 2:
The patent replaces mechanical/physical measurement systems (specialized sensors, depth sensors, 3D scanners) with an optical-computational system. Instead of using mechanical depth sensing devices or stereo imaging elements, the system uses 2D camera images combined with neural network processing to achieve body composition analysis, substituting physical measurement mechanisms with information processing.
2Measurement precision
If expensive specialized sensors are used, then body composition measurement accuracy is improved, but ease of operation deteriorates
Solution Approach 1:
The patent employs inexpensive 2D camera images instead of expensive, specialized sensing equipment. The system uses standard digital cameras or smartphone cameras to capture images, which are then processed computationally. This approach makes the technology accessible to ordinary users without requiring investment in specialized medical or scientific equipment.
Solution Approach 2:
The system enables users to perform their own body composition analysis without requiring professional operators or complex setup procedures. Users simply capture 2D images of themselves, and the automated neural network processing generates body fat measurements and 3D models independently, making the service self-performed and highly accessible.
3Ease of operation
If standard two-dimensional cameras are used, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent transforms two-dimensional image data into three-dimensional body models through computational processing. By using neural networks to infer depth, volume, and spatial relationships from 2D images, the system effectively adds dimensional information that was not directly captured by the camera, enabling accurate body composition analysis from planar images.
Solution Approach 2:
The system changes the processing parameters and computational approach to extract meaningful body composition data from 2D images. Instead of relying on the camera's native measurement capabilities, the neural networks analyze image parameters (pixel intensities, gradients, textures, geometric relationships) and transform them into body fat percentage and other composition metrics through learned relationships.
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
Described are systems and methods directed to generation of a personalized three-dimensional ("3D") body model of a body, such as a human body, based on two-dimensional ("2D") images of that body and the generation and presentation of predicted personalized 3D body models of the body when one or more body measurements (e.g., body fat, body weight, muscle mass) are changed. For example, a user may provide a target body measurement value and the implementations will generate one or more predicted personalized 3D body models representative of a predicted appearance of the body with the target body measurement value.