Avatar Generation System Using Multi-Timing Video Capture

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for generating avatars based on captured images often result in unsatisfactory outcomes due to variations in image capture conditions, such as brightness, color, and angle, leading to undesired avatars and requiring user pre-settings for skin color or hairstyle.

Innovation Solution

A portable information-processing device captures a video of a subject, using facial recognition to identify features and generate multiple avatars based on different image capture timings, allowing users to select their desired avatar without explicit recapture instructions, employing a system with image capture, generation, and display means to provide a range of avatar options.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If a single captured image is used to generate an avatar, then the generation process is simple and fast, but the avatar accuracy and user satisfaction deteriorate due to variations in capture conditions

Engineering Contradiction:
Improveavatar generation speedVSAvoidavatar accuracy
Core Design Contradiction:
ProductivityVSManufacturing precision

Solution Approach 1:

The system performs preliminary actions by capturing multiple images under varying conditions before avatar generation. Instead of waiting for perfect capture conditions, the system proactively captures a series of images with different brightness, color, and angle variations, then processes these pre-captured images to generate accurate avatars, thereby resolving the contradiction between generation speed and accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system applies parameter changes by intentionally varying capture conditions (brightness, color, angle) across multiple images. By generating avatars from images with diverse parameter settings rather than a single fixed condition, the system achieves higher avatar accuracy while maintaining efficient processing through automated multi-parameter analysis.

Inventive Principle:
Principle #35Parameter changes

2Manufacturing precision

If user pre-settings for skin color or hairstyle are required, then avatar accuracy can be improved, but the ease of operation deteriorates due to additional configuration steps

Engineering Contradiction:
Improveavatar accuracyVSAvoidoperation simplicity
Core Design Contradiction:
Manufacturing precisionVSEase of operation

Solution Approach 1:

The system implements self-service by automatically analyzing captured images to extract skin color, hairstyle, and other appearance features without requiring user pre-settings. The avatar generation process autonomously determines these parameters from the image data itself, eliminating the need for manual user configuration while maintaining high avatar accuracy.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system replaces the mechanical interaction of manual user configuration with automated image analysis processing. Instead of requiring users to manually set skin color or hairstyle parameters, the system uses computational algorithms to automatically extract these features from captured images, substituting user operation with automated mechanical processing.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If multiple avatars are generated from different capture timings, then user options and satisfaction improve, but the device complexity and processing time increase

Engineering Contradiction:
Improveavatar option diversityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system applies segmentation by dividing the avatar generation process into independent processing stages: capturing multiple images at different timings, analyzing each image separately to extract features, and generating individual avatars from each analysis. This segmented approach enables diverse avatar options while managing system complexity through modular, independent processing units.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system uses periodic action by capturing images at regular time intervals and generating avatars periodically from each captured image. This structured periodic processing provides users with multiple avatar options from different capture timings while maintaining manageable system complexity through predictable, rhythmic operation cycles.

Inventive Principle:
Principle #19Periodic action

Data Source

PatentEP3047884B1Program, information-processing device, information-processing system, and avatar generating method
Publication Date: 2020.11.18 NINTENDO CO LTD
  • EP3047884B1 patent drawingFigure 1~2
  • EP3047884B1 patent drawingFigure 3~4
  • EP3047884B1 patent drawingFigure 5~6

AI summary

An example information-processing device (10) includes an image capture means (110) for capturing a video of a subject, an image generation means (120) for generating plural avatars based on plural images constituting the video captured by the image capture means (110), the plural images corresponding respectively to different image capture timings, each of the plural avatars representing a subject shown in one of the plural images, and a display means (130) for displaying the plural avatars generated by the image generation means (120).