Semantic understanding of 3d data

Patent metadata

Field	Value
Publication number	US-2016055268-A1
Application number	US-201414298370-A
Country	US
Kind code	A1
Filing date	Jun 6, 2014
Priority date	Jun 6, 2014
Publication date	Feb 25, 2016
Grant date	—

Abstract

Systems and techniques for processing three-dimensional (3D) data are presented. Captured three-dimensional (3D) data associated with a 3D model of an architectural environment is received and at least a portion of the captured 3D data associated with a flat surface is identified. Furthermore, missing data associated with the portion of the captured 3D data is identified and additional 3D data for the missing data is generated based on other data associated with the portion of the captured 3D data.

First claim

What is claimed is:

1 . A system, comprising:
a memory storing computer executable components; and a processor configured to execute the following computer executable components stored in the memory:
an identification component that receives captured three-dimensional (3D) data associated with a 3D model of an architectural environment and identifies at least a portion of the captured 3D data associated with a flat surface; and
a data generation component that identifies missing data associated with the portion of the captured 3D data and generates additional 3D data for the missing data based on other data associated with the portion of the captured 3D data.

2 . The system of claim 1 , wherein the identification component identifies another portion of the captured 3D data associated with an object.

3 . The system of claim 2 , wherein the identification component identifies the missing data associated with the portion of the captured 3D data based on boundary data associated with the other portion of the captured 3D data.

4 . The system of claim 2 , wherein the data generation component identifies the other portion of the captured 3D data associated with the object based on proximity data in relation to the portion of the captured 3D data.

5 . The system of claim 2 , wherein the identification component generates an object relation identifier for the portion of the captured 3D data associated with the flat surface and the other portion of the captured 3D data associated with the object.

6 . The system of claim 2 , further comprising a modification component that modifies position or orientation of the other portion of the captured 3D data associated with the object.

7 . The system of claim 6 , wherein the modification component modifies the position or the orientation of the other portion of the captured 3D data associated with the object based on input received via a user interface.

8 . The system of claim 1 , wherein the identification component identifies an opening associated with the portion of the captured 3D data.

9 . The system of claim 8 , wherein the identification component classifies the opening as a window opening or a door opening based on information associated with the opening.

10 . The system of claim 1 , wherein the identification component classifies the portion of the captured 3D data surface as a floor, a wall or a ceiling based on orientation information associated with the portion of the captured 3D data.

11 . The system of claim 1 , wherein the identification component defines a boundary associated with the flat surface.

12 . The system of claim 1 , further comprising a modification component that modifies geometry data or texture data for the portion of the captured 3D data.

13 . The system of claim 12 , wherein the modification component modifies the geometry data or the texture data for the portion of the captured 3D data based on input data received via a user interface.

14 . The system of claim 12 , wherein the modification component determines illumination data associated with the texture data that is applied when modifying the texture data.

15 . A method, comprising:
employing a processor that facilitates execution of computer executable instructions stored on a non-transitory computer readable medium to implement operations, comprising: receiving captured three-dimensional (3D) data associated with a 3D model of an architectural environment; identifying at least a portion of the captured 3D data associated with a flat plane; identifying omitted data associated with the portion of the captured 3D data; and generating other 3D data for the omitted data based on the portion of the captured 3D data.

16 . The method of claim 15 , further comprising identifying another portion of the captured 3D data associated with an object.

17 . The method of claim 16 , wherein the identifying the omitted data comprises identifying the omitted data associated with the portion of the captured 3D data based on at least one border of the other portion of the captured 3D data.

18 . The method of claim 16 , wherein the identifying the other portion of the captured 3D data associated with the object comprises identifying the other portion of the captured 3D data associated with the object based on texture data associated with the portion of the captured 3D data and the other portion of the captured 3D data.

19 . The method of claim 16 , further comprising generating object relation data associated with the portion of the captured 3D data and the other portion of the captured 3D data.

20 . The method of claim 15 , further comprising identifying a rectangular opening associated with the portion of the captured 3D data.

21 . The method of claim 15 , further comprising:
identifying another portion of the captured 3D data associated with another flat plane; and reclassifying the portion of the captured 3D data and the other portion of the captured 3D data as corresponding data based on at least distance data associated with the portion of the captured 3D data and the other portion of the captured 3D data.

22 . The method of claim 21 , wherein the reclassifying comprises reclassifying the portion of the captured 3D data and the other portion of the captured 3D data as the corresponding data based on orientation data associated with the portion of the captured 3D data and the other portion of the captured 3D data.

23 . The method of claim 15 , further comprising modifying geometry data or texture data for the portion of the captured 3D data based on data received via a user interface.

24 . A computer readable storage device comprising instructions that, in response to execution, cause a system comprising a processor to perform operations, comprising:
receiving three-dimensional (3D) data associated with a 3D model of an architectural environment; identifying at least a portion of the 3D data associated with a flat surface and missing data associated with the portion of the 3D data; and generating additional 3D data for the missing data based on the portion of the 3D data.

Assignees

• Matterport Inc

Inventors

• Bell Matthew Tschudy
• Gausebeck David Alan
• Ford Daniel
• Coombe Gregory William

Classifications

• G06T19/00 Primary

  Manipulating three-dimensional [3D] models or images for computer graphics · CPC title

• G06F30/13

  Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads · CPC title

• G06T2210/04

  Architectural design, interior design · CPC title

• G06T17/00

  Three-dimensional [3D] modelling for computer graphics · CPC title

• G06V20/00

  Scenes; Scene-specific elements (control of digital cameras H04N23/60) · CPC title