Automatic Virtual Object Creation from Source Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for generating artificial reality environments require manual creation and precise placement of virtual objects, which is time-consuming and requires technical expertise, especially when recreating real-world locations, often resulting in deficient object correspondence.
Innovation Solution
An artificial reality environment creation system that uses machine learning models to analyze source images, generate object identifiers, and create 3D models with textures, allowing for automatic selection and placement of virtual objects without the need for manual input or technical expertise.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual creation and placement of virtual objects is used, then precise object correspondence can be achieved, but the process becomes time-consuming and requires technical expertise
Solution Approach 1:
The system performs automatic image analysis, object identification, and virtual object generation without requiring manual intervention. The machine learning models autonomously process source images to create accurate virtual representations, eliminating the need for technical expertise while maintaining precision.
Solution Approach 2:
Manual mechanical processes of object creation and placement are replaced with automated machine learning systems. The ML models analyze images and generate virtual objects algorithmically, substituting human manual work with intelligent automated processing that maintains accuracy while dramatically reducing time requirements.
2Manufacturing precision
If manual creation and placement of virtual objects is used, then precise object correspondence can be achieved, but technical expertise is required
Solution Approach 1:
The system autonomously performs all tasks from image analysis to virtual object generation without human intervention. Users simply provide source images, and the machine learning system handles the complex processing automatically, making the operation simple while maintaining high precision through intelligent algorithms.
Solution Approach 2:
Machine learning models serve as intermediaries between the user's simple image input and the complex task of creating accurate virtual objects. The ML systems translate straightforward image data into precise virtual representations, bridging the gap between simple operation and high precision output.
3Productivity
If automatic machine learning-based creation is used, then time consumption is reduced and ease of operation is improved, but the system complexity increases
Solution Approach 1:
The system creates virtual copies of real-world objects from source images using machine learning. These digital replicas capture the essential characteristics of physical objects, enabling fast automatic generation while the complexity is contained within the ML models themselves rather than requiring complex user operations.
Data Source
AI summary
Methods and systems described herein are directed to creating an artificial reality environment having elements automatically created from source images. In response to a creation system receiving the source images, the system can employ a multi-layered comparative analysis to obtain virtual object representations of objects depicted in the source images. A first set of the virtual objects can be selected from a library by matching identifiers for the depicted objects with tags on virtual objects in the library. A second set of virtual objects can be objects for which no candidate first virtual objects was adequately matched in the library, prompting the creation of a virtual object by generating depth data and skinning a resulting 3D mesh based on the source images. Having determined the virtual objects, the system can compile them into the artificial reality environment according to relative locations determined from the source images.