Granted Patent B2

US 12,705,828 · App. 18/541,711 · Granted Aug 11, 2026

Inventors: Charles Dasher (Lawrenceville, GA); Reda Harb (Tampa, FL)

Assignee: Adeia Guides Inc.

G06T17/00G06T7/12G06T7/20G06V10/44G06V10/764G06V2201/07

Abstract

Claims (72)

1 . A method for scanning a physical object, the method comprising:

detecting, by control circuitry, a presence of the physical object to be scanned in an extended reality environment;

initiating, by the control circuitry, a 3D scan of the physical object as a background operation of a user device;

in response to the initiation of the 3D scan, capturing, by the control circuitry, scan data corresponding to the object while the object is in a field of view of the user device;

calculating, by the control circuitry, a confidence score based on the scan data, wherein the confidence score is used to determine whether to continue the 3D scan;

applying, by the control circuitry, spatial segmentation to the scan data to identify regions of interest, and bypass segments of the physical object that have been previously captured and remain unchanged;

performing, by the control circuitry, model quantization on the scan data, wherein a degree of the quantization is adjusted based on the availability of cloud computing resources;

storing, by the control circuitry, the scan data in a database in response to the calculated confidence score exceeding a threshold; and

generating, by the control circuitry, a 3D model of the physical object in the extended reality environment based on the scan data in the database.

2 . The method of claim 1 , further comprising:

initiating a primary 3D scan of the physical object as a background operation of the user device;

based on the primary 3D scan data, determining that a 3D model related to the physical object is incomplete;

retrieving the 3D model related to the physical object from the database; and

updating the retrieved 3D model with the scan data.

3 . The method of claim 1 , wherein, in response to detecting the presence of the object, the method further comprises:

displaying an assistive user interface element around the object on a viewport of the user device to capture a plurality of angles of the object in a 3D space.

4 . The method of claim 1 , further comprising:

determining completion status data for the generation of the 3D model;

generating an overlay comprising the 3D model on the object based on the completion status data; and

displaying the overlay within the viewport of the user device.

5 . The method of claim 1 , wherein:

applying the spatial segmentation to the scan data to identify regions of interest further comprises:

distinguishing the physical object from background elements in the field of view;

extracting a set of data points corresponding to pertinent sections of the physical object to restrict an area of focus for the 3D scan; and

storing a plurality of detailed segmentations of the identified regions of interest in the database for use as a spatial reference during a subsequent encounter with the physical object.

6 . The method of claim 1 , further comprising:

receiving an indication of priority for scanning one or more objects of a plurality of objects; and

capturing the one or more objects of the plurality of objects based on the indication of priority.

7 . The method of claim 1 , further comprising:

tracking a motion of the physical object; and

capturing the scan data corresponding to the physical object based on a speed of the motion of the object, wherein the scan data is captured when the speed of the motion is within a pre-defined threshold.

8 . The method of claim 1 , wherein generating the 3D model comprises:

receiving a set of features of interest corresponding to the object; and

generating the 3D model based on the set of features of interest.

9 . The method of claim 1 , further comprising:

creating at least one classifier algorithm based on the scan data of the physical object; and

using the classifier algorithm to detect a presence of a second physical object.

10 . A system for scanning a physical object, the system comprising control circuitry configured to:

detect a presence of the physical object to be scanned in an extended reality environment;

initiate a 3D scan of the physical object as a background operation of a user device;

in response to the initiation of the 3D scan, capture scan data corresponding to the object while the object is in a field of view of the user device;

calculate a confidence score based on the scan data, wherein the confidence score is used to determine whether to continue the 3D scan;

apply spatial segmentation to the scan data to identify regions of interest and bypass segments of the physical object that have been previously captured and remain unchanged;

perform model quantization on the scan data, wherein a degree of the quantization is adjusted based on the availability of cloud computing resources;

store the scan data in a database in response to the calculated confidence score exceeding a threshold; and

generate a 3D model of the physical object in the extended reality environment based on the scan data in the database.

11 . The system of claim 10 , the control circuitry configured to:

retrieve a prior 3D model related to the physical object from the database;

determine whether the prior 3D model related to the physical object is complete; and

in response to determining the prior 3D model is not complete, update the retrieved prior 3D model with the scan data.

12 . The system of claim 10 , wherein, in response to detecting the presence of the object, the control circuitry configured to:

display an assistive user interface element around the object on a viewport of the user device to capture a plurality of angles of the object in a 3D space.

13 . The system of claim 10 , the control circuitry configured to:

determine completion status data for the generation of the 3D model;

generate an overlay comprising the 3D model on the object based on the completion status data; and

display the overlay on the viewport of the user device.

14 . The system of claim 10 , wherein the control circuitry is configured, when applying spatial segmentation to the scan data to identify regions of interest, to:

distinguish the physical object from background elements in the field of view while applying the spatial segmentation;

extract a set of data points corresponding to pertinent sections of the physical object to restrict an area of focus for the 3D scan; and

store a plurality of detailed segmentations of the identified regions of interest in the database for use as a spatial reference during a subsequent encounter with the physical object.

15 . The system of claim 11 , the control circuitry configured to:

receive an indication of priority for scanning one or more of a plurality of objects; and

capture each of the plurality of objects based on the indication of priority.

16 . The system of claim 10 , the control circuitry configured to:

track a motion of the physical object; and

capture the scan data corresponding to the physical object based on a speed of the motion of the object, wherein the scan data is captured when the speed of the motion is within a pre-defined threshold.

17 . The system of claim 10 , the control circuitry configured to:

receive a set of features of interest corresponding to the object; and

generate the 3D model based on the set of features of interest.

18 . The system of claim 10 , the control circuitry configured to:

create at least one classifier algorithm based on the scan data of the physical object; and

use the classifier algorithm to detect a presence of a second physical object.

Assignments (1)

Continuity (1)

References Cited (53)