AR Space Matching for Automatic Virtual Object Placement

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional AR/MR experiences rely on user intervention for placing and sizing virtual objects, leading to potential confusion and a negative user experience due to incorrect rendering of virtual objects in the real-world environment.

Innovation Solution

A computing device uses sensors and machine learning models to generate a 3D representation of the real-world environment, automatically matching virtual objects to available spaces, adjusting their size and orientation to fit seamlessly within the environment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If user intervention is used for placing and sizing virtual objects, then the user can control the position and size of virtual objects, but the user experience deteriorates due to confusion and negative interaction with the real-world environment

Engineering Contradiction:

Improveuser control over virtual objectsVSAvoiduser experience quality

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system performs automatic environment scanning, space identification, and virtual object placement without requiring user intervention. The computing device autonomously captures images, generates 3D representations, identifies available spaces, and positions virtual objects, allowing the system to serve itself rather than relying on user control operations.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary scanning and analysis of the real-world environment before virtual object placement. By pre-generating 3D representations and identifying suitable spaces in advance, the system prepares the environment model beforehand, enabling accurate and context-appropriate virtual object placement without requiring user trial-and-error adjustments.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If automatic placement is implemented using machine learning models, then the user experience improves through seamless integration, but the device complexity increases due to sensors and processing requirements

Engineering Contradiction:

Improvevirtual object integration qualityVSAvoidsystem configuration

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The computing device integrates multiple functions into a single system: it acts as a scanner using sensors, a 3D model generator, a space identifier, and a virtual object placer. The machine learning model serves as a universal component that processes environment data and determines optimal placement, consolidating what would otherwise require separate specialized devices or manual operations.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system replaces manual mechanical interaction (user physically manipulating virtual objects) with automated computational processes. Machine learning models and image processing algorithms substitute for user hand-eye coordination and spatial reasoning, using digital computation rather than physical user actions to achieve accurate virtual object placement.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If manual manipulation is required for virtual objects to fit the environment, then the placement flexibility is maintained, but the productivity decreases due to time-consuming setup processes

Engineering Contradiction:

Improvevirtual object placement flexibilityVSAvoidAR/MR experience setup speed

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system autonomously determines the optimal placement of virtual objects by analyzing the scanned environment and applying machine learning models. This self-service capability eliminates the need for manual user manipulation while maintaining adaptability to the specific real-world context, thereby significantly reducing setup time and improving productivity.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS12475656B2Space and content matching for augmented and mixed reality

Publication Date: 2025.11.18 DISNEY ENTERPRISES INC

AI summary

Techniques for automatically placing and manipulating virtual objects of augmented reality (AR) and mixed reality (MR) simulations are described. One technique includes obtaining an indication of at least one virtual object available for placing within a real-world environment during an AR simulation or a MR simulation. A first representation of the real-world environment is generated, based on a scan of the real-world environment. At least one second representation of the real-world environment is generated from the first representation. A match is determined between the at least one virtual object and at least one available space within the real-world environment, based at least in part on evaluating the at least one virtual object and the at least one second representation with a machine learning model(s). The at least one virtual object is rendered on a computing device, based on the match.