Granted Patent B2

US 12,505,670 · App. 18/084,053 · Granted Dec 23, 2025

Inventors: Aaron K. Baughman (Cary, NC); Sarbajit K. Rakshit (Kolkata, IN); Micah Forster (Round Rock, TX); Kavitha Hassan Yogaraj (Bangalore, IN)

Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION

G06V20/41G06V10/235G06V10/764G06V20/46

Abstract

Claims (58)

1 . A computer-implemented method comprising:

selecting, using a first attribute of a first object, the first object in a first volumetric video;

selecting, using a second attribute of a second object, the second object in a second volumetric video, wherein the first attribute and the second attribute satisfy an aggregation rule;

generating an aggregated volumetric video from the first volumetric video and the second volumetric video, wherein the generating of the aggregated video comprises rendering the first object and the second object simultaneously in the aggregated volumetric video based on the aggregation rule;

detecting a user input from a user indicative of a selection of the first volumetric video; and

determining whether the user is authorized to view the first volumetric video by comparing a permission rule associated with the user to an access rule associated with the first volumetric video, wherein the generating of the aggregated volumetric video is responsive to determining that the user is authorized to view the first volumetric video.

2 . The method of claim 1 , wherein the selecting of the first object in the first volumetric video comprises using an instance segmentation process, wherein the instance segmentation process comprises classifying a first portion of the first volumetric video as being representative of the first object having the first attribute.

3 . The method of claim 2 , wherein instance segmentation process further comprises:

extracting an image segment from a frame of the first volumetric video;

classifying the extracted image segment using a trained machine-learning based image classifier, wherein the image classifier outputs a segment classification in response to receiving the extracted image segment;

determining that the segment classification output from the image classifier is associated with the first object having the first attribute;

designating, responsive to determining that the segment classification is associated with the first object having the first attribute, the extracted image segment as a depiction of at least some of the first object such that the first portion of the first volumetric video comprises the extracted image segment.

4 . The method of claim 2 , further comprising:

extracting the first portion of the first volumetric video from frames of the first volumetric video; and

inserting the thus extracted first portion of the first volumetric video into frames of a third volumetric video.

5 . The method of claim 4 , further comprising:

extracting a second portion of the second volumetric video from frames of the second volumetric video, wherein the second portion is representative of the second object having the second attribute; and

inserting the thus extracted second portion of the second volumetric video into frames of a third volumetric video.

6 . The method of claim 1 , further comprising:

transmitting the aggregated volumetric video to a user device;

detecting a user input indicative of a selection of the first volumetric video; and

transitioning, responsive to the user input, from transmitting the aggregated volumetric video to the user device to transmitting the first volumetric video to the user device.

7 . The method of claim 1 , further comprising:

transmitting a multiview selection image to a user device, wherein the multiview selection image comprises a preview image associated with the aggregated volumetric video;

detecting a user input indicative of a selection of the preview image; and

transmitting, responsive to the user input, the aggregated volumetric video to the user device.

8 . The method of claim 1 , further comprising:

comparing a first set of aggregation rules associated with a first user to a second set of aggregation rules associated with a second user;

detecting that the first set of aggregation rules matches the second set of aggregation rules, wherein the first set of aggregation rules and the second set of aggregation rules both include said aggregation rule; and

transmitting, responsive to detecting that the first set of aggregation rules matches the second set of aggregation rules, the aggregated volumetric video to the first user and to the second user.

9 . The method of claim 8 , further comprising:

designating, responsive to detecting that the first set of aggregation rules matches the second set of aggregation rules, the first user and the second user for collective aggregation processing.

10 . The method of claim 9 , further comprising:

transmitting, responsive to designating the first user and the second user for collective aggregation processing, the aggregated volumetric video to a first user device associated with the first user and to a second user device associated with the second user.

11 . A computer program product comprising one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by a processor to cause the processor to perform operations comprising:

selecting, using a first attribute of a first object, the first object in a first volumetric video;

selecting, using a second attribute of a second object, the second object in a second volumetric video, wherein the first attribute and the second attribute satisfy an aggregation rule;

generating an aggregated volumetric video from the first volumetric video and the second volumetric video, wherein the generating of the aggregated video comprises rendering the first object and the second object simultaneously in the aggregated volumetric video based on the aggregation rule;

detecting a user input from a user indicative of a selection of the first volumetric video; and

determining whether the user is authorized to view the first volumetric video by comparing a permission rule associated with the user to an access rule associated with the first volumetric video, wherein the generating of the aggregated volumetric video is responsive to determining that the user is authorized to view the first volumetric video.

12 . The computer program product of claim 11 , wherein the stored program instructions are stored in a computer readable storage device in a data processing system, and wherein the stored program instructions are transferred over a network from a remote data processing system.

13 . The computer program product of claim 11 , wherein the stored program instructions are stored in a computer readable storage device in a server data processing system, and wherein the stored program instructions are downloaded in response to a request over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system, further comprising:

program instructions to meter use of the program instructions associated with the request; and

program instructions to generate an invoice based on the metered use.

14 . The computer program product of claim 11 , the operations further comprising:

transmitting the aggregated volumetric video to a user device;

detecting a user input indicative of a selection of the first volumetric video; and

transitioning, responsive to the user input, from transmitting the aggregated volumetric video to the user device to transmitting the first volumetric video to the user device.

15 . The computer program product of claim 11 , the operations further comprising:

transmitting a multiview selection image to a user device, wherein the multiview selection image comprises a preview image associated with the aggregated volumetric video;

detecting a user input indicative of a selection of the preview image; and

transmitting, responsive to the user input, the aggregated volumetric video to the user device.

16 . A computer system comprising a processor and one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by the processor to cause the processor to perform operations comprising:

selecting, using a first attribute of a first object, the first object in a first volumetric video;

selecting, using a second attribute of a second object, the second object in a second volumetric video, wherein the first attribute and the second attribute satisfy an aggregation rule;

generating an aggregated volumetric video from the first volumetric video and the second volumetric video, wherein the generating of the aggregated video comprises rendering the first object and the second object simultaneously in the aggregated volumetric video based on the aggregation rule;

detecting a user input from a user indicative of a selection of the first volumetric video; and

determining whether the user is authorized to view the first volumetric video by comparing a permission rule associated with the user to an access rule associated with the first volumetric video, wherein the generating of the aggregated volumetric video is responsive to determining that the user is authorized to view the first volumetric video.

Assignments (1)

Continuity (1)

References Cited (31)