公开(公告)号：US20240379127A1

公开(公告)日：2024-11-14

申请号：US18314112

申请日：2023-05-08

Applicant: Apple Inc.

Inventor： Rupamay Saha ,  Shaun M. Poole

IPC: G11B27/031 ,  G06T5/00

Abstract: 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.

公开(公告)号：US20240378850A1

公开(公告)日：2024-11-14

申请号：US18314095

申请日：2023-05-08

Applicant: Apple Inc.

Inventor： Paul M. Bombach ,  James C. Arndt ,  David N. Chen ,  Todd E. Kramer ,  Shaun M. Poole ,  Rupamay Saha ,  Eugene M. Walden

IPC: G06V10/70 ,  H04N7/01

Abstract: In one or more embodiments, a computing device is configured to modify an original video by applying a machine learning model. The computing device obtains multiple training data sets, with each particular training data set including an original video and a corresponding modified video. One or more frames from the original video are cropped to generate corresponding frames in the corresponding modified video. The computing device trains a machine learning model, using the training data sets, to generate modified videos from original videos such that one or more frames in the original videos are modified to generate corresponding frames in respective modified videos. Once the machine learning model is trained, the computing device obtains a target original video and applies the trained machine learning model to the target original video to generate a target modified video.

公开(公告)号：US20240378767A1

公开(公告)日：2024-11-14

申请号：US18314104

申请日：2023-05-08

Applicant: Apple Inc.

Inventor： Daniel Pettigrew ,  Robert J. Bell ,  Peter H. Chou ,  Michael J. Garber ,  Shaun M. Poole

IPC: G06T11/00 ,  G06F3/04847 ,  G06T5/00

Abstract: A computing device harmonizes output image properties displayed on a graphical user interface (GUI) when a user switches between two or more images of different image formats to display on the GUI. When a user interacts with a user interface to change one or more display properties of an image, a system modifies displayed image properties based on the user's modifications. If the user selects another image with different dynamic range than the first image, the system performs a backend image conversion so that the displayed properties of the second image correspond to the user-selected modifications to the displayed properties of the first image.

公开(公告)号：US20240380945A1

公开(公告)日：2024-11-14

申请号：US18314101

申请日：2023-05-08

Applicant: Apple Inc.

Inventor： David C. Schweinsberg ,  Gregory E. Niles ,  Shaun M. Poole ,  Peter A. Steinauer

IPC: H04N21/472 ,  G06F3/04883 ,  H04N21/431

Abstract: In one or more embodiments, a computing device is configured to present playback of a media composition on a touchscreen display. Concurrently with presenting the playback, the computing device receives, via the touchscreen display during a first time period, a touch input that includes a series of motions that start when a particular frame of the media composition is being presented. Responsive to receiving the touch input: the computing device adds a media clip to the media composition, with the media clip including a graphical representation of the touch input, having a duration corresponding to the first time period, and being stored in association with the particular frame. Subsequent to adding the media clip, the computing device presents a second playback of the media composition where playback of the media clip is initiated when playback of the particular frame is started during the second playback of the media composition.