Virtual Try-On Spectacles Sizing via 3D Facial Mesh Collision

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing virtual try-on systems struggle with accurately sizing and positioning spectacles frames on a user's face due to lack of three-dimensional information, leading to unrealistic results and requiring user input that can be inaccurate and time-consuming.

Innovation Solution

Capture a user's image and obtain three-dimensional location information using sensors, overlay a virtual representation of spectacles based on this information, and perform iterative intersection tests to determine the precise size and position, using a facial coordinate system and collision detection to ensure realistic placement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional augmented reality systems are used to overlay virtual spectacles on user images, then the virtual objects can be displayed, but the sizing and positioning are inaccurate due to lack of three-dimensional information

Engineering Contradiction:
Improvesizing precisionVSAvoidthree-dimensional information
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The patent transitions from two-dimensional image processing to three-dimensional spatial modeling by creating a three-dimensional coordinate system and generating a three-dimensional mesh model of the user's face. This dimensional upgrade enables accurate sizing and positioning of virtual spectacles by providing depth information and spatial relationships that are absent in conventional 2D approaches.

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

Solution Approach 2:

The patent introduces a three-dimensional mesh model as an intermediary representation between the captured image and the virtual spectacles overlay. This mesh model serves as a mediator that encodes facial geometry and spatial relationships, enabling precise placement and scaling of virtual objects without requiring direct three-dimensional sensing of the actual spectacles.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If user input is required for accurate positioning, then positioning accuracy may improve, but the process becomes time-consuming

Engineering Contradiction:
Improvepositioning precisionVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs automatic facial landmark detection and three-dimensional mesh generation without requiring user input for positioning. The algorithm autonomously identifies facial features, constructs the coordinate system, and determines the optimal placement of virtual spectacles, eliminating the need for manual user adjustments while maintaining high positioning precision.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent performs preliminary processing by pre-generating the three-dimensional facial mesh model and pre-establishing the coordinate system before overlaying the virtual spectacles. This preliminary setup automates the positioning process, eliminating the need for time-consuming user input during the actual try-on experience.

Inventive Principle:
Principle #10Preliminary action

3Manufacturing precision

If iterative intersection tests are performed to determine precise size and position, then accuracy improves, but computational complexity increases

Engineering Contradiction:
Improveplacement precisionVSAvoidcomputational complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent segments the complex positioning problem into manageable components: first establishing a three-dimensional coordinate system, then generating a facial mesh model, followed by iterative intersection tests for size determination, and finally position optimization. This segmentation allows the system to achieve high precision while managing computational complexity through structured problem decomposition.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3830799B1Virtual try-on systems and methods for spectacles
Publication Date: 2026.02.04 WARBY PARKER INC
  • EP3830799B1 patent drawingFigure 1
  • EP3830799B1 patent drawingFigure 2
  • EP3830799B1 patent drawingFigure 3

AI summary

Various aspects of the subject technology relate to systems, methods, and machine-readable media for virtual try-on of items such as spectacles. A virtual try-on interface may be implemented at a server or at a user device, and may use collision detection between three-dimensional models of the spectacles and of a user's face and head to determine the correct size and position of the spectacles for virtual try-on. With the determined size and position, a virtual representation of the spectacles is superimposed on an image of the user.