Flexible Device Bending Estimation for AR/VR Depth Alignment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Inaccurate depth sensing due to bending of flexible devices in augmented and virtual reality systems, leading to misalignment errors and inefficiencies in computing resources.

Innovation Solution

A method for generating biometric data based on bending estimation of flexible devices, using visual tracking systems to correct depth maps and authenticate users by training models on bending patterns, thereby improving depth sensing accuracy and reducing resource usage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If flexible devices are used in AR/VR systems, then adaptability and comfort are improved, but depth sensing accuracy deteriorates due to bending

Engineering Contradiction:

ImproveadaptabilityVSAvoiddepth sensing accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system continuously monitors device bending through visual tracking and feeds this information back to correct depth maps in real-time, maintaining accurate depth sensing despite the flexible device's inherent bending

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system changes the parameter representation by transforming depth data from the bent device coordinate system to a corrected reference frame, accounting for bending-induced distortions through parameter transformation rather than physical rigidity

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If continuous depth sensing is performed on flexible devices, then tracking accuracy is improved, but computational resources are consumed excessively

Engineering Contradiction:

Improvetracking accuracyVSAvoidcomputational resources

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary bending estimation and correction factor calculation during idle periods or low-activity phases, preparing correction data in advance so that during active tracking, only lightweight applications of pre-computed corrections are needed, reducing real-time computational burden

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If bending correction algorithms are applied, then depth sensing accuracy is improved, but device complexity increases

Engineering Contradiction:

Improvedepth sensing accuracyVSAvoiddevice complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system introduces an intermediary bending estimation module that acts as a mediator between the visual tracking system and depth sensing components, translating complex bending physics into simplified correction parameters that can be applied without significantly increasing overall system complexity

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12475202B2Bending estimation as a biometric signal

Publication Date: 2025.11.18 SNAP INC

AI summary

A method for generating reference biometric data based on a bending of a flexible device is described. In one aspect, a method includes forming training data includes bending estimates of a flexible device worn by a first user, training a model based on the training data, and generating reference biometric data for the first user based on the model.