Avatar Region Classification for Realistic Virtual Fitting

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users face challenges in virtually trying on clothing using large format display devices, as they cannot accurately predict how clothing will look when worn, and the service is not well-suited to changing seasons and surroundings.

Innovation Solution

An electronic device that captures a user's image, sets an avatar region, generates an avatar based on body information, and combines it with the user's image to create a composite display, allowing for a realistic virtual fitting service by classifying the display into a mirror region and an avatar region.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a user views clothing on an avatar or model displayed on an LFD device, then the user can see how the clothing looks on others, but the user cannot accurately predict how the clothing will look when actually worn

Engineering Contradiction:
Improveprediction accuracyVSAvoidvirtual fitting experience
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent creates a virtual copy (avatar) of the user's actual body by capturing images with a camera and generating a three-dimensional avatar model. This copy allows the user to see how clothing would look on their own body shape and features, providing accurate prediction while maintaining the convenience of virtual fitting.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent transitions from two-dimensional images displayed on traditional screens to three-dimensional avatars that can be viewed from multiple angles. This dimensional enhancement allows users to rotate and examine the avatar with clothing from different perspectives, significantly improving prediction accuracy of how the clothing will look when worn.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Adaptability or versatility

If traditional virtual fitting services are used, then clothing can be viewed on a model, but the service is not well-suited to changing seasons and surroundings

Engineering Contradiction:
Improveseasonal and environmental adaptabilityVSAvoidfitting service suitability
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent implements dynamic backgrounds that can change according to different seasons, times of day, and environments. Instead of static model images, the system allows users to place their three-dimensional avatar in various virtual settings (e.g., beach for summer, snowy landscape for winter), making the fitting service adaptable to changing seasons and surroundings while maintaining reliable suitability assessment.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent creates a universal virtual fitting platform that works across different seasons, locations, and clothing types. The three-dimensional avatar can be dressed in any clothing item and placed in any virtual environment, making the service universally applicable regardless of seasonal or environmental changes.

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

3Ease of operation

If an LFD device is used for virtual fitting, then large format display provides visual information, but the display does not provide a natural and realistic virtual fitting service

Engineering Contradiction:
Improvevisual information displayVSAvoidrealism of fitting visualization
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent changes the key parameter of visualization from two-dimensional flat images to three-dimensional models with depth, volume, and spatial orientation. This parameter change allows the avatar to be rotated 360 degrees and viewed from any angle, providing a natural and realistic representation of how clothing drapes and fits on the body, while still utilizing the large format display for comprehensive visual information.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS11232512B2Method and device for combining an avatar image with a portion of a user's image
Publication Date: 2022.01.25 SAMSUNG ELECTRONICS CO LTD
  • US11232512B2 patent drawing
  • US11232512B2 patent drawing
  • US11232512B2 patent drawing

AI summary

A method and an electronic device for composing an image are provided. An electronic device includes a display configured to display an image of a user photographed by a camera; an input component configured to receive a user input; a communicator configured to facilitate a communication with an external server; and a processor configured to display the image of the user on the display, set an avatar region within the image of the user based on the received user input, generate an avatar to be displayed on the avatar region, and control the display to combine the avatar with the image of the user and to display the resulting composite image.