Samsung patents video method keeping main objects consistent across scenes
Samsung describes a method for generating videos where a specific main object looks the same in every scene. The system identifies this object, uses a trained model to create its visual details, and ensures it appears consistently throughout the final video.
In the filing’s own words
An electronic device according to one embodiment may comprise a memory for storing instructions, and a processor. When executed by the processor, the instructions can instruct the electronic device to identify first information associated with descriptions corresponding to a plurality of scenes, identify, on the basis of the first information, at least one main object included in at least some of the plurality of scenes, input descriptions corresponding to the at least one main object into a first model trained to output content on the basis of the reception of information associated with scenes, thereby acquiring, on the basis of information output from the first model, first content corresponding to the at least one main object, and, on the basis of the first information and the information about the first content, acquire a video including the plurality of scenes. The at least one main object can be consistently visualized in at least some of the plurality of scenes.
What exactly they claim (claim 1)
1. An electronic device comprising: memory storing instructions; and a processor, wherein the instructions, when executed by the processor individually or collectively, cause the electronic device to: identify first information associated with a description corresponding to a plurality of scenes, based on the first information, identify at least one main object included in at least a portion of the plurality of scenes, based on information output from a first model by inputting a description corresponding to the at least one main object into the first model trained to output content based on receiving information associated with a scene, obtain first content corresponding to the at least one main object, and based on the first information and information on the first content, obtain a video including the plurality of scenes, wherein the at least one main object is consistently visualized in the at least a portion of the plurality of scenes.
Facts
- Company
- Samsung (Samsung Electronics Co., Ltd.)
- Official title
- METHOD FOR PROVIDING VIDEO, ELECTRONIC DEVICE FOR SUPPORTING SAME, AND STORAGE MEDIUM
- Publication number
- US20260290048A1
- Application number
- 19689152
- Filed
- May 27, 2026
- Published
- Sep 24, 2026
- Inventors
- 5
- Claims
- 15
Classified under
G06V 20/60 Physics & computingG06T 11/60 Physics & computingMore from Samsung in AI & software
- Samsung patents tool to erase objects from photos using AI Sep 24, 2026
- Samsung patents drawing objects into photos with AI Oct 15, 2026
- Samsung patents AI that creates personalized exercise videos Sep 10, 2026
- Samsung patents AI summaries for paused TV shows based on your viewing habits Sep 24, 2026
- Samsung patents turning chat conversations into image prompts Oct 1, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.