3D Avatar Generation from Depth and Skeletal Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current video game avatars do not accurately represent players' appearances, as manual customization is time-consuming and does not yield a resemblance to the player, despite advancements in processing power and graphics.

Innovation Solution

A system that captures a player's current appearance using visible spectrum images, depth images, and skeletal data to generate a 3D avatar, including facial appearance, hair, clothing, and skin color, by identifying and warping facial features, matching hair styles, and detecting clothing boundaries, allowing for an accurate representation of the player.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual customization is used to create an avatar, then the player can select features such as hair color, gender, and height, but the process is time-consuming and the avatar does not accurately resemble the player's actual appearance

Engineering Contradiction:
Improveaccuracy of avatar resemblanceVSAvoidtime for customization
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent captures the player's actual appearance through imaging devices and creates a digital copy by mapping captured features (facial structure, hair, clothing, skin color) directly to the avatar model, eliminating manual customization and achieving accurate resemblance automatically

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system performs preliminary capture and analysis of the player's appearance features before avatar generation, storing these captured attributes for direct application to the avatar, thus eliminating the need for time-consuming manual selection during the avatar creation process

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If simple predefined characters are used, then the game can be implemented with basic graphics, but the player cannot achieve a realistic representation of themselves

Engineering Contradiction:
Improverealism of player representationVSAvoidsystem complexity for avatar generation
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the player's appearance into distinct segments (facial features, hair, clothing, skin color) and captures each separately using specific imaging devices, then applies these segmented attributes to corresponding parts of the avatar model to achieve realistic representation

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary processing layer that captures raw appearance data, processes and analyzes the features, and then maps them to the avatar model, mediating between the simple input (player standing still) and the complex output (realistic 3D avatar)

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP2718902B1Generation of avatar reflecting player appearance
Publication Date: 2017.07.26 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP2718902B1 patent drawingFigure 1
  • EP2718902B1 patent drawingFigure 2~4
  • EP2718902B1 patent drawingFigure 5

AI summary

Systems, methods, and computer media for generating an avatar reflecting a player's current appearance. Data describing the player's current appearance is received. The data includes a visible spectrum image of the player, a depth image including both the player and a current background, and skeletal data for the player. The skeletal data indicates an outline of the player's skeleton. Based at least in part on the received data, one or more of the following are captured: a facial appearance of the player; a hair appearance of the player; a clothing appearance of the player; and a skin color of the player. A 3D avatar resembling the player is generated by combining the captured facial appearance, hair appearance, clothing appearance, and/or skin color with predetermined avatar features.