Augmented Reality Image Augmentation via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality content systems rely on user input for generating image augmentations, limiting creativity and realism in augmented reality experiences.
Innovation Solution
A custom augmentation system utilizing machine learning models to generate image augmentation decisions without user input, leveraging segmentation, classification, object detection, or saliency models to provide contextual and realistic modifications to images within augmented reality content items.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If user input is required to generate image augmentations, then user control and customization are improved, but system complexity and user burden increase
Solution Approach 1:
The machine learning model automatically analyzes the input image and generates augmentation decisions without requiring user input or interaction. The system serves itself by autonomously determining which augmentations to apply based on image content analysis, thereby eliminating user burden while maintaining customization.
Solution Approach 2:
The patent replaces the manual user interaction mechanism with an automated machine learning-based decision system. Instead of users manually selecting augmentations, the system uses computer vision and machine learning models to automatically generate augmentation decisions, substituting mechanical user input with intelligent automation.
2Ease of operation
If machine learning models are used to generate image augmentations automatically, then ease of operation is improved, but device complexity increases
Solution Approach 1:
The patent introduces machine learning models as intermediary components between the input image and the augmentation application. These models act as mediators that automatically analyze image content and generate augmentation decisions, simplifying the user interface while managing system complexity through modular architecture.
Solution Approach 2:
The system segments the augmentation process into distinct functional components: image input, machine learning analysis, decision generation, and augmentation application. This segmentation allows each component to be optimized independently, managing overall system complexity while enabling automated operation.
3Manufacturing precision
If contextual analysis is performed using machine learning, then realism and quality of augmentations are improved, but processing time and computational resources increase
Solution Approach 1:
The machine learning models perform preliminary analysis of the input image to pre-determine augmentation decisions before the actual augmentation is applied. This preliminary action enables the system to prepare augmentation strategies in advance, reducing real-time processing delays while maintaining high augmentation quality.
Data Source
AI summary
Systems and methods herein describe receiving an image via an image capture device, using a machine learning model, generating an image augmentation decision, accessing an augmented reality content item, associating the generated image augmentation decision with the augmented reality content item, modifying the received image using the augmented reality content item and the associated image augmentation decision, and causing presentation of the modified image on a graphical user interface of a computing device.