Virtual Avatar Generation Using Depth Sensor Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current virtual reality systems lack effective methods to generate immersive virtual entities representing real-world users, limiting user immersion and interaction within virtual environments.

Innovation Solution

A system utilizing imaging devices, depth sensors, physical processors, and computer program instructions to create virtual entities by modifying base body and head models based on user appearance data, incorporating machine learning techniques to determine correspondence values and generate accurate virtual representations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If virtual entities are generated using traditional methods, then the system complexity is reduced, but the level of immersion and realism is insufficient

Engineering Contradiction:
Improverealism of virtual entityVSAvoidsystem complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system segments the virtual entity generation process into distinct modules: image capture module, depth sensing module, processing module, and rendering module. Each module handles a specific aspect of the pipeline, allowing complex processing to be broken down into manageable components that can be optimized independently while maintaining overall system realism.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system creates accurate visual copies of real-world users by capturing their appearance through imaging devices and depth sensors, then reproducing these characteristics in the virtual environment. This copying approach enables realistic virtual entities without requiring complex procedural generation, as the system directly replicates observed visual properties.

Inventive Principle:
Principle #26Copying

2Measurement precision

If detailed user appearance data is captured to improve virtual entity accuracy, then the representation quality increases, but the data processing time and computational resources increase

Engineering Contradiction:
Improveaccuracy of user representationVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary capture of user appearance data using imaging devices and depth sensors before the virtual entity needs to be rendered. By capturing and processing appearance information in advance, the system prepares the necessary data structures and parameters ahead of time, reducing the computational burden during actual virtual environment interactions and minimizing processing delays.

Inventive Principle:
Principle #10Preliminary action

3Manufacturing precision

If multiple sensors and imaging devices are used to capture comprehensive user data, then the quality of virtual entity generation improves, but the cost and complexity of the system setup increases

Engineering Contradiction:
Improvequality of virtual entityVSAvoidsystem setup ease
Core Design Contradiction:
Manufacturing precisionVSEase of manufacture

Solution Approach 1:

The system employs multi-functional components that serve multiple purposes: imaging devices capture both visual appearance and spatial information, depth sensors provide both geometric data and distance measurements, and the processing module handles various tasks including feature extraction, matching, and parameter calculation. This multi-functionality reduces the need for separate specialized devices, simplifying system setup while maintaining high virtual entity quality.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS10846903B2Single shot capture to animated VR avatar
Publication Date: 2020.11.24 DISNEY ENTERPRISES INC
  • US10846903B2 patent drawing
  • US10846903B2 patent drawing
  • US10846903B2 patent drawing

AI summary

Presented herein are systems and methods configured to generate virtual entities representing real-world users. In some implementations, the systems and/or methods are configured to capture user appearance information with imaging devices and sensors, determines correspondence values conveying correspondences between the appearance of the user's body or user's head and individual ones of default body models and/or default head models, modifies a set of values defining a base body model and/or base head model based on determined correspondence values and sets of base values defining the default body models and/or default head models. The base body model and/or base head model may be modified to model the appearance of the body and/or head of the user.