Granted Patent B2

US 12,417,601 · App. 18/163,905 · Granted Sep 16, 2025

Inventors: Shailendra Moyal (Pune, IN); Sarbajit K. Rakshit (Kolkata, IN)

Assignee: International Business Machines Corporation

G06T19/20G06T15/20G06T2200/24G06T2219/2004

Abstract

Claims (61)

1. A processor-implemented method, the method comprising:

generating a volumetric video from a multi-camera feed;

presenting the generated volumetric video to a user;

receiving one or more user inputs to the presented volumetric video;

modifying the volumetric video based on the one or more user inputs, wherein the modifying further comprises:

capturing a second volumetric video;

identifying a deviation between the generated volumetric video and the second volumetric video associated with the one or more user inputs; and

modifying the generated volumetric video by the deviation so that an area associated with a user input within the one or more user inputs in the generated volumetric video corresponds to a value associated with the second volumetric video; and

presenting the modified volumetric video to the user.

2. The method of claim 1 , wherein the receiving further comprises:

receiving a user selection of one or more objects of the generated volumetric video; and

receiving an action to perform on each user selection.

3. The method of claim 2 , wherein the modifying further comprises:

generating a second volumetric video corresponding to an area around each user selection;

performing the action to the one or more objects in the second volumetric video; and

replacing a segment of the generated volumetric video that corresponds to the second volumetric video.

4. The method of claim 3 , wherein the modifying further comprises:

performing one or more consistency modifications to the generated volumetric video outside the area around each user selection that adapt each object in the generated volumetric video to minimize an impact of the replaced segment to the generated volumetric video.

5. The method of claim 1 , wherein the modifying is performed through a generative adversarial network.

6. The method of claim 1 , wherein the one or more user inputs are selected from a group consisting of an addition action, a deletion action, and a modification action.

7. A computer system, the computer system comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:

generating a volumetric video from a multi-camera feed;

presenting the generated volumetric video to a user;

receiving one or more user inputs to the presented volumetric video;

modifying the volumetric video based on the one or more user inputs, wherein the modifying further comprises:

capturing a second volumetric video;

identifying a deviation between the generated volumetric video and the second volumetric video associated with the one or more user inputs; and

modifying the generated volumetric video by the deviation so that an area associated with a user input within the one or more user inputs in the generated volumetric video corresponds to a value associated with the second volumetric video; and

presenting the modified volumetric video to the user.

8. The computer system of claim 7 , wherein the receiving further comprises:

receiving a user selection of one or more objects of the generated volumetric video; and

receiving an action to perform on each user selection.

9. The computer system of claim 8 , wherein the modifying further comprises:

generating a second volumetric video corresponding to an area around each user selection;

performing the action to the one or more objects in the second volumetric video; and

replacing a segment of the generated volumetric video that corresponds to the second volumetric video.

10. The computer system of claim 9 , wherein the modifying further comprises:

performing one or more consistency modifications to the generated volumetric video outside the area around each user selection that adapt each object in the generated volumetric video to minimize an impact of the replaced segment to the generated volumetric video.

11. The computer system of claim 7 , wherein the modifying is performed through a generative adversarial network.

12. The computer system of claim 7 , wherein the one or more user inputs are selected from a group consisting of an addition action, a deletion action, and a modification action.

13. A computer program product, the computer program product comprising:

one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more tangible storage medium, the program instructions executable by a processor capable of performing a method, the method comprising:

generating a volumetric video from a multi-camera feed;

presenting the generated volumetric video to a user;

receiving one or more user inputs to the presented volumetric video;

modifying the volumetric video based on the one or more user inputs, wherein the modifying further comprises:

capturing a second volumetric video;

identifying a deviation between the generated volumetric video and the second volumetric video associated with the one or more user inputs; and

modifying the generated volumetric video by the deviation so that an area associated with a user input within the one or more user inputs in the generated volumetric video corresponds to a value associated with the second volumetric video; and

presenting the modified volumetric video to the user.

14. The computer program product of claim 13 , wherein the receiving further comprises:

receiving a user selection of one or more objects of the generated volumetric video; and

receiving an action to perform on each user selection.

15. The computer program product of claim 14 , wherein the modifying further comprises:

generating a second volumetric video corresponding to an area around each user selection;

performing the action to the one or more objects in the second volumetric video; and

replacing a segment of the generated volumetric video that corresponds to the second volumetric video.

16. The computer program product of claim 15 , wherein the modifying further comprises:

performing one or more consistency modifications to the generated volumetric video outside the area around each user selection that adapt each object in the generated volumetric video to minimize an impact of the replaced segment to the generated volumetric video.

17. The computer program product of claim 13 , wherein the modifying is performed through a generative adversarial network.

Assignments (1)

Continuity (1)

References Cited (16)