Neural AR Content Extension via Machine Learning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current augmented reality (AR) environments require a time- and resource-intensive process to combine traditional media content with physical space layouts, involving multiple teams and manual placement of AR assets, which limits efficiency and diversity of content.

Innovation Solution

A machine learning model is used to input a physical space layout and anchor content, generating an augmented reality view that seamlessly extends the anchor content across the space, allowing for automatic and efficient combination of traditional media with physical space layouts.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If manual processes are used to convert traditional media content into AR assets and place them within AR environments, then the AR content can be customized and positioned accurately, but the process becomes time-consuming and resource-intensive

Engineering Contradiction:
ImproveAR asset positioning accuracyVSAvoidContent generation time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical processes of AR asset creation and positioning with an automated machine learning system. The neural network model automatically generates AR content and determines its placement within physical spaces based on input images and spatial data, eliminating the need for manual conversion and positioning operations while maintaining accuracy through learned patterns and algorithms

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If multiple teams of artists and developers work on converting and positioning AR assets, then the AR content quality can be maintained, but the resource consumption increases significantly

Engineering Contradiction:
ImproveAR content qualityVSAvoidTeam structure complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent implements self-service by enabling the machine learning system to autonomously perform both content generation and positioning tasks without requiring multiple specialized teams. The neural network model independently processes input media, generates appropriate AR assets, and determines their optimal placement based on spatial relationships, replacing the need for coordinated work between art teams and development teams

Inventive Principle:
Principle #25Self-service

3Adaptability or versatility

If conventional AR content generation methods are used, then the process is controllable and predictable, but the diversity and availability of AR content is limited

Engineering Contradiction:
ImproveAR content diversityVSAvoidContent creation ease
Core Design Contradiction:
Adaptability or versatilityVSEase of manufacture

Solution Approach 1:

The patent applies parameter changes by using the machine learning model to generate AR content with varied characteristics based on different input media and spatial configurations. The system can adjust content parameters such as style, scale, and positioning based on the input image and detected physical space, enabling diverse AR content generation while maintaining ease of use through automated processing

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4404144A1Neural extension of 2d content in augmented reality environments
Publication Date: 2024.07.24 DISNEY ENTERPRISES INC
  • EP4404144A1 patent drawingFigure 1
  • EP4404144A1 patent drawingFigure 2A
  • EP4404144A1 patent drawingFigure 2B

AI summary

One embodiment of the present invention sets forth a technique for generating augmented reality content. The technique includes inputting a first layout of a physical space and a first set of anchor content into a machine learning model. The technique also includes generating, via execution of the machine learning model, a first augmented reality view that includes (i) a first portion of the physical space and (ii) an extension of the first set of anchor content across a second portion of the physical space. The technique further includes causing the first augmented reality view to be outputted in a computing device.