3D Image Augmentation for Preserving Object Spatial Relationships

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image augmentation methods struggle to maintain the spatial relationships of objects when converting between 2D and 3D environments, leading to unrealistic augmentations.

Innovation Solution

A method that identifies key objects and spatial relationships in both images, uses 3D coordinate spaces to insert 3D models while preserving these relationships, and employs algorithms like RANSAC and Hough to determine coordinate spaces, along with machine learning for interior design rules.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If objects are manually inserted into a room design application, then the augmentation process is simple to operate, but the spatial configuration does not take into consideration the spatial relationships of real objects present in the augmented scene

Engineering Contradiction:
Improveease of object insertionVSAvoidspatial relationship accuracy
Core Design Contradiction:
Ease of operationVSManufacturing precision

Solution Approach 1:

The patent replaces manual mechanical insertion operations with an automated computer vision system that uses image processing algorithms to automatically detect objects, determine their 3D coordinates, and insert them with correct spatial relationships. The system substitutes human manual placement with automated image analysis and coordinate transformation processes.

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

Solution Approach 2:

The system enables self-service by automatically analyzing the uploaded image, identifying objects within it, determining their spatial relationships, and placing them in the augmented reality scene without requiring manual user configuration. The computer vision system performs the entire spatial configuration task autonomously.

Inventive Principle:
Principle #25Self-service

2Adaptability or versatility

If 2D image data is converted to 3D environment, then the visualization capability is improved, but the original intent of the 2D image spatial relationships is lost

Engineering Contradiction:
Improvevisualization capabilityVSAvoidspatial relationship preservation
Core Design Contradiction:
Adaptability or versatilityVSManufacturing precision

Solution Approach 1:

The patent applies dimensionality change by extracting 3D coordinate information from 2D images and transforming them into a 3D augmented reality environment. The system uses coordinate transformation algorithms to map 2D image coordinates to 3D space while preserving the relative spatial relationships between objects, enabling accurate placement in the augmented scene.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Device complexity

If multiple objects are inserted with manual configuration, then the device complexity is low, but the time required for augmentation increases

Engineering Contradiction:
Improvesystem complexityVSAvoidaugmentation speed
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The system performs preliminary action by pre-processing the uploaded image to identify all objects and their spatial relationships before the actual augmentation process. The computer vision system analyzes the image structure, determines object positions and orientations, and prepares the configuration data in advance, which significantly speeds up the subsequent augmentation process.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual configuration operations with automated image processing and object recognition algorithms. The system automatically extracts spatial information from the image, determines coordinate transformations, and configures multiple objects simultaneously without requiring repeated manual interventions for each object.

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

Data Source

PatentEP4111423B1A computer implemented method, a device and a computer program product for augmenting a first image with image data from a second image
Publication Date: 2026.01.28 INTER IKEA SYST
  • EP4111423B1 patent drawingFigure 1~2
  • EP4111423B1 patent drawingFigure 3
  • EP4111423B1 patent drawingFigure 4

AI summary

A method for inserting objects from a 2D image into another environment while keeping the spatial relationships of the objects in the 2D image intact is provided. A device comprising circuitry configured to carry out the method and a computer program product adapted to carry out the method are also provided.