Apple patents video tool that swaps focus between subjects after filming
Apple describes a video editing feature that lets users change which person or object is sharp and which is blurry after a video has already been recorded. The system identifies the subjects in the footage and applies digital sharpening or softening to create new versions of the clip with different focus points.
In the filing’s own words
In some implementations, a system generates a video clip in which the user can select which entity is in-focus and which other entities are out-of-focus based on a source video clip that has already been recorded. Multiple video clips may be generated based on the source video clip with different selected entities in-focus and other entities out-of-focus. In other implementations, a system overlays an image grid on frames of a video clip and analyzes the frames based on annotation criteria to determine which portions of the frames, corresponding to respective cells of the image grid, meet the annotation criteria. The system overlays an annotation on the cells of the image grid indicative of a portion of the frames meeting the annotation criteria while refraining from overlaying the annotation on any cells of the image grid indicative of a portion of the frames that do not meet the annotation criteria.
What exactly they claim (claim 1)
1. A non-transitory computer readable medium comprising one or more sequences of instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising: receiving a first video clip comprising a first set of frames, wherein the first video clip is generated by concurrently recording a first entity and a second entity using an image capture device; wherein the first entity is (a) displayed within each of the first set of frames and (b) is in-focus in each of the first set of frames, and wherein the second entity is (a) displayed within each of the first set of frames and (b) is out-of-focus in each of the first set of frames; receiving user input requesting a second video clip where the second entity is in-focus; responsive to receiving the user input, generating a second video clip comprising a second set of frames with: the second entity being displayed in-focus within each of the second set of frames; and the first entity being displayed out-of-focus within each of the second set of frames; wherein generating the second video clip comprises: determining, for each of the first set of frames, a first set of image portions corresponding to the first entity; and softening the first set of image portions corresponding to the first entity to render the first entity out-of-focus; determining, for each of the first set of frames, a second set of image portions corresponding to the second entity; sharpening the second set of image portions corresponding to the second entity to render the second entity in-focus; and storing the second video clip.
Facts
- Company
- Apple (Apple Inc.)
- Official title
- Scene removal, cinematic video editing, and image grid operations in video editing application
- Patent number
- US12771898B2
- Application number
- 18314112
- Filed
- May 8, 2023
- Granted
- Oct 20, 2026
- Inventors
- 2
- Claims
- 19
Classified under
H04N 21/4312 Electricity & electronicsG06F 3/04847 Physics & computingG06F 3/0488 Physics & computingG06F 3/04883 Physics & computingG06T 5/70 Physics & computingG06T 5/73 Physics & computingMore from Apple in AI & software
- Apple patents AI that acts on voicemails for you Oct 15, 2026
- Apple patents letting users teach custom hand gestures to their devices Oct 22, 2026
- Apple patents AI that acts on voicemails for you Sep 1, 2026
- Apple patents system that changes room ambience based on what you look at Sep 3, 2026
- Apple patents voice commands that use cameras to find specific devices Sep 17, 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.