3D Building Visual Models From External Imagery for Rapid Navigation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing technologies face challenges in effectively capturing, representing, and using building information, including visual data of interiors and exteriors, without physical travel, and constructing and maintaining accurate floor plans and computer models.

Innovation Solution

Automated generation of 3D Gaussian Splat models or 3D spatial radiance field models from captured external imagery, allowing real-time rendering of building images from various view poses and integrating additional data for improved navigation and presentation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If floor plans or computer models are used to represent building information, then some information about room layout and building details can be provided, but the models are difficult to construct and maintain, and hard to accurately scale and populate with interior information

Engineering Contradiction:
Improvebuilding information completenessVSAvoidmodel construction and maintenance complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent creates visual copies of building exteriors and interiors by capturing images from multiple viewpoints and synthesizing them into immersive visual models. These visual models serve as accurate representations without requiring manual construction of traditional floor plans or computer models, eliminating the complexity of creating and maintaining such models while preserving complete building information.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical process of manually constructing and maintaining floor plans and computer models with an automated image-based system. By using captured images and computational algorithms to generate visual models, the system eliminates the manual effort required to create and update traditional building representations, while maintaining accurate scaling and interior information.

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

2Ease of operation

If traditional computer models are used to visualize building exteriors and interiors, then some spatial information can be provided, but the models are difficult to use in relation to surroundings and require significant computing power and time

Engineering Contradiction:
Improvebuilding model usabilityVSAvoidcomputing power and time required
Core Design Contradiction:
Ease of operationVSPower

Solution Approach 1:

The patent creates visual copies of building exteriors and interiors by capturing images from multiple viewpoints and synthesizing them into immersive visual models. These visual models serve as accurate representations without requiring manual construction of traditional floor plans or computer models, eliminating the complexity of creating and maintaining such models while preserving complete building information.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent creates a universal visual representation system that can be used for multiple purposes including navigation, presentation, analysis, and exploration of building exteriors and interiors. The same visual model generated from captured images serves all these functions simultaneously, eliminating the need for separate specialized models for different applications and reducing overall computational requirements.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP4672158A1Automated generation and use of visual models of buildings using at least captured external imagery
Publication Date: 2025.12.31 MFTB HOLDCO INC
  • EP4672158A1 patent drawingFigure 1A
  • EP4672158A1 patent drawingFigure 1B
  • EP4672158A1 patent drawingFigure 2A

AI summary

Techniques are described for automatically generating visual model representations of buildings based at least in part on captured external imagery of the buildings, and using the generated building visual models to generate and present new images and optionally in additional manners, such as to improve navigation of a building and/or its surroundings. The described techniques may include acquiring building data from a plurality of exterior acquisition locations at multiple heights and view angles of an exterior of a building (e.g., using a flying drone and/or other flying device that captures the data), generating visual model representation(s) of the building (e.g., a 3D Gaussian Splat model), and using the generated visual model representation(s) to generate and present a new image with a view of the building exterior from a particular pose along with associated user-manipulatable controls.