Real-Time 3D AR Object Upscaling for High-Resolution Acquisition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing augmented reality (AR) technologies require high-spec hardware and are limited by low real-time data processing capabilities and low image quality, particularly in generating high-definition (HD) or ultra HD (UHD) content.

Innovation Solution

A real-time 3D AR object acquisition system that includes an image acquisition device and a 3D AR object acquisition device, utilizing an RGB camera, depth camera, LiDAR sensor, and radar sensor to create a 3D AR object in real time, and an upscale module to enhance image resolution by a factor of n, converting low-resolution images into high-resolution images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If existing AR technologies use high-spec hardware for high-definition content generation, then image quality is improved, but device complexity and cost increase

Engineering Contradiction:
Improveimage qualityVSAvoidhardware specification
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent creates a 3D copy of the target object by capturing images from multiple angles and generating a three-dimensional model. This digital 3D AR object can be manipulated and displayed without requiring high-spec hardware for the original object, thus improving image quality while reducing device complexity requirements

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces complex mechanical/hardware-based high-definition rendering with a software-based 3D modeling and image processing system. By using multiple standard cameras and computational algorithms to create 3D AR objects, the system achieves high-definition content generation without relying on high-spec hardware

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

2Productivity

If existing AR technologies process data in real time, then responsiveness is improved, but processing speed and computational power requirements increase

Engineering Contradiction:
Improvereal-time processing capabilityVSAvoiddata processing power
Core Design Contradiction:
ProductivityVSPower

Solution Approach 1:

The patent segments the 3D AR object creation process into distinct stages: image capture from multiple angles, feature point detection, 3D model generation, and rendering. This segmentation allows each stage to be processed efficiently and independently, enabling real-time processing while reducing the computational power required at any single moment

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary actions by pre-processing images to detect feature points and pre-generating 3D models before final rendering. This preparation work is done in advance so that when real-time interaction is needed, the system can quickly render the pre-prepared 3D AR objects without requiring excessive computational power during the interaction phase

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20250239033A1Real-time 3D ar object acquisition device, system, and method
Publication Date: 2025.07.24 KOREA ELECTRONICS TECH INST
  • US20250239033A1 patent drawing
  • US20250239033A1 patent drawing
  • US20250239033A1 patent drawing

AI summary

Proposed are a real-time three-dimensional (3D) augmented reality (AR) object acquisition device, system, and method that makes it possible to acquire a high-resolution 3D AR object in real time. The system may include an image acquisition device for acquiring a plurality of images required to create a 3D AR object of a subject in real time, and a 3D AR object acquisition device for acquiring a high-resolution 3D AR object in real time on the basis of the plurality of images. The 3D AR object acquisition device may include a 3D AR object creation module that uses the plurality of images to create the 3D AR object in real time, and an upscale module that upscales the resolution of each frame of an image of the created 3D AR object by a factor of n to convert the 3D AR object into a high-resolution 3D AR object in real time.