Systems And Methods For Processing 2D/3D Data For Structures Of Interest In A Scene And Wireframes Generated Therefrom

Patent No. US11043026 (titled "Systems And Methods For Processing 2D/3D Data For Structures Of Interest In A Scene And Wireframes Generated Therefrom") was filed by Pointivo Inc on Jan 28, 2018.

What is this patent about?

’026 is related to the field of generating wireframe renderings from 2D and 3D data. Existing methods for creating these renderings, especially for complex structures like buildings, often require manual intervention to ensure accuracy. This is because current algorithms struggle to automatically resolve geometric features without human assistance, particularly when dealing with non-standard or complex designs.

The underlying idea behind ’026 is to automatically generate accurate wireframe renderings by extracting specific geometric primitives directly from processed 3D data. Instead of relying on predefined shapes from a library, the invention identifies and isolates fundamental geometric forms (planes, ellipsoids, etc.) present in the data, and uses these primitives to construct the wireframe. This approach allows for the accurate representation of arbitrary or complex structures without manual intervention.

The claims of ’026 focus on a method that involves providing 2D and 3D data for a structure of interest, processing this data to generate 3D information representing the structure's edges, and then extracting at least one geometric primitive from this information. The extracted primitives, representing object surfaces, are selected from a predefined list (Table 1 in the patent). The method then processes the output to create a wireframe rendering, determining edges, intersections, and spatial relationships between object surfaces, and combining these to generate the final rendering.

The invention works by first processing 2D images and 3D point clouds to generate 3D data with boundary information. This processed data is then analyzed to identify and extract the geometric primitives. The extracted primitives are combined, taking into account their spatial relationships and intersections, to create the wireframe. The process can also incorporate machine learning to refine the wireframe's geometry and appearance, ensuring accuracy and consistency.

’026 differentiates itself from prior approaches by using a data-driven method that extracts geometric primitives directly from the processed 3D data, rather than relying on a model-driven approach that fits predefined shapes to the data. This allows the system to accurately represent complex or non-standard structures without needing a library of predefined shapes. The resulting wireframe renderings are numerically accurate, with measurements and dimensions closely matching the actual structure.

How does this patent fit in bigger picture?

Technical landscape at the time

In the late 2010s when ’026 was filed, 3D modeling and wireframe generation at a time when systems commonly relied on point cloud data obtained from LiDAR or similar techniques. At this time, generating accurate wireframe renderings automatically, especially for complex or non-standard structures, was non-trivial due to limitations in computer vision algorithms and the need for manual intervention.

Novelty and Inventive Step

The examiner allowed the claims because the combination of resolving edges of object surfaces based on intersections, spatial relationships, and multiple 2D images, along with combining the resolved object surfaces to generate a wireframe rendering, was not disclosed in the prior art. The examiner also stated that there was no motivation to combine the references to meet the limitations of the claims.

Claims

This patent contains 18 claims, with independent claims numbered 1 and 9. The independent claims are directed to methods of generating wireframe renderings of structures of interest using 2D and 3D data. The dependent claims generally add further details or limitations to the methods described in the independent claims.

Key Claim Terms New

Definitions of key terms used in the patent claims.

Term (Source)Support for SpecificationInterpretation
Edge or skeletal representation
(Claim 1, Claim 9)
“The 2D and 3D data is processed to generate 3D information comprising an edge or skeletal representation associated with the at least one structure of interest. From such processed information, at least one geometric primitive is extracted therefrom, where the extracted geometric primitive(s) are selected from a specific list as set out in Table 1 hereinafter.”A representation of the structure of interest derived from processing 2D and 3D data, used for extracting geometric primitives.
Geometric primitive
(Claim 1, Claim 9)
“From such processed information, at least one geometric primitive is extracted therefrom, where the extracted geometric primitive(s) are selected from a specific list as set out in Table 1 hereinafter. From the at least one extracted geometric primitives, a wireframe rendering of at least part of the structure of interest in the scene is provided. Yet further, at least two geometric primitives can be extracted from the processed information, wherein all or part of the first geometric primitive is within the second geometric primitive boundary.”An object surface of the structure of interest, selected from a list of geometric primitives in Table 1, and extracted from 3D information comprising an edge or skeletal representation.
Structure of interest
(Claim 1, Claim 9)
“The present invention relates to systems and methods for generating wireframe renderings of one or more structures of interest in a scene. The structure of interest optionally comprises at least one non-planar surface. The types of structures of interest that can be used with the inventions herein are expansive. For example, the structures can comprise building exteriors or interiors. The structure of interest can comprise a roof.”A building, part of a building, or other object in a scene for which a wireframe rendering is to be generated.
Wireframe rendering
(Claim 1, Claim 9)
“Digital three dimensional (“3D”) building models, such as wireframe renderings, are increasingly used for diverse tasks in architecture and design such as construction planning, visualization, navigation, simulation, facility management, renovation, and retrofitting. As one example, when manipulated to generate a wireframe rendering, 3D data in the form of point clouds can be used in CAD systems, building information model (“BIM”) systems, A/R (“augmented reality”) or V/R (“virtual reality”) or the like.”A digital three-dimensional model of a structure or object, generated from 2D and 3D data, for use in applications such as CAD systems, building information models, augmented reality, or virtual reality.

Litigation Cases New

US Latest litigation cases involving this patent.

Case NumberFiling DateTitle
8:25-cv-00576Mar 10, 2025Pointivo, Inc. V. 5X5 Technologies, Inc.

Patent Family

Patent Family

File Wrapper

The dossier documents provide a comprehensive record of the patent's prosecution history - including filings, correspondence, and decisions made by patent offices - and are crucial for understanding the patent's legal journey and any challenges it may have faced during examination.

  • Date

    Description

  • Get instant alerts for new documents

US11043026

POINTIVO INC
Application Number
US15881795
Filing Date
Jan 28, 2018
Status
Granted
Expiry Date
Feb 21, 2039
External Links
Slate, USPTO, Google Patents