Optical Pupillary Distance Measurement for Virtual Eyewear Try-On
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for remotely measuring pupillary distance in virtual try-on of eyewear are inaccurate due to errors from incorrect assumptions about the distance and alignment of objects relative to the camera, and the use of cumbersome clip-on fiducial accessories introduces cost, fragility, and usability issues, while virtual try-on systems struggle to balance instant gratification and maximum accuracy in rendering eyewear fit.
Innovation Solution
A method using a single RGB camera to measure pupillary distance by tracking eye movements without clip-on fiducials, and a hybrid approach for virtual try-on that provides real-time results with instant gratification while background processing for maximum accuracy, incorporating smart eyewear adjustability constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a known-sized object (e.g., credit card) is held against the user's forehead for scale reference, then pupillary distance measurement can be performed remotely, but measurement accuracy deteriorates due to errors from incorrect assumptions about distance and alignment relative to the camera
Solution Approach 1:
The patent introduces fiducial markers as intermediary elements that are integrated into the camera system itself rather than requiring external objects. These markers serve as a stable reference frame that mediates between the camera and the user's face, enabling accurate scale and distance calculations without relying on user-held objects or complex alignment procedures
Solution Approach 2:
The patent replaces the mechanical alignment process (manually holding an object at specific distances and angles) with an optical/computational solution. The fiducial markers in the camera provide automatic geometric reference, substituting the need for mechanical positioning and manual alignment with automated image processing and coordinate transformation algorithms
2Measurement precision
If clip-on fiducial accessories are used to enable optical measurements, then measurement capability is improved, but device complexity, cost, and fragility increase
Solution Approach 1:
The patent merges the fiducial reference system with the camera itself by integrating fiducial markers directly into the camera housing or mounting structure. This combination eliminates the need for separate clip-on accessories, reducing system complexity while maintaining measurement capability. The camera and fiducial system become a unified measurement device
Solution Approach 2:
The camera system with integrated fiducial markers performs its own calibration and measurement functions without requiring external accessories or complex setup procedures. The fiducial markers embedded in the camera enable the system to self-determine scale, distance, and alignment parameters automatically, making the system self-sufficient and eliminating fragile external components
3Manufacturing precision
If virtual try-on rendering is performed with maximum accuracy processing, then rendering quality is improved, but processing time increases and instant gratification is reduced
Solution Approach 1:
The patent applies partial processing by performing essential calculations immediately for instant gratification (basic scale estimation, rough positioning) while deferring more computationally intensive operations (precise 3D reconstruction, detailed rendering) to background processing. This allows the system to provide satisfactory results quickly while continuing to refine accuracy without blocking user interaction
Solution Approach 2:
The patent performs preliminary calculations and estimations before the user completes the full measurement sequence. Initial scale and positioning are determined from early frames or partial data, allowing immediate rendering feedback. Subsequent frames and measurements are then used to refine and correct these preliminary results in the background, providing both instant gratification and maximum accuracy
Data Source
AI summary
Systems and methods are disclosed for determining optical measurements for adjusting virtual try-on glasses. The method includes receiving a digital input including an image of a user's face and a known-sized object, wherein the known-sized object is positioned against a screen adjacent to a camera of a user device. A plurality of instructions is generated in a user interface of the user device for tracking eye movements of the user, wherein the plurality of instructions advises the user to look at the first feature of the known-sized object, a second feature of the known-sized object, and into a distance beyond the known-sized object. A scaled reconstruction of the user's face and/or a recommendation on virtual try-on glasses is generated based on the tracking of the eye movements and/or calculations based on equations.