公开(公告)号：US10417276B2

公开(公告)日：2019-09-17

申请号：US15594992

申请日：2017-05-15

Applicant: Adobe Inc.

Inventor： Tulika Garg ,  Neeraj Goel

IPC: G06F17/30 ,  H04N5/232 ,  H04N5/262 ,  H04N1/393 ,  G06T3/40 ,  G06F16/583 ,  G06F3/0482 ,  H04N1/387 ,  G06F16/54 ,  G06T3/00 ,  G06T11/60

Abstract: Generating thumbnails from panoramic images is described. In one or more implementations, a 2D projection of a panoramic image is received and projected onto a 3D surface to generate a 3D projection. Portions of the 3D projection are formed, and each portion is projected to a 2D plane to generate 2D projections of the portions. Object recognition is then performed on the portions that identifies objects, attributes of the objects, and locations of the objects within the panoramic image. Responsive to an image search query matching one of the recognized objects, the system generates a thumbnail from the panoramic image specific to a portion of the panoramic image that contains the object and outputs the thumbnail.

公开(公告)号：US10356456B2

公开(公告)日：2019-07-16

申请号：US14933995

申请日：2015-11-05

Applicant: ADOBE INC.

Inventor： Angela Ranjeet ,  Kiran Chandra Zagabattuni ,  Pavan Kumar Bvn ,  Niraj Gupta ,  Neeraj Goel

IPC: H04N21/25 ,  H04N21/45 ,  G11B27/031 ,  H04N21/234 ,  H04N21/258 ,  H04N21/466 ,  H04N21/8549

Abstract: A dynamically created video preview can be provided to a viewer by stitching relevant video clips from a target video based on a viewer profile of the viewer. In various embodiments, a computer receives a request from a viewer to preview a video. The computer can then select one or more clips from the video based on the viewer profile of the viewer. Thereafter, the computer can generate a customized video preview from the one or more selected clips for the viewer based on the viewer profile. Other embodiments may be described and/or claimed.

公开(公告)号：US11086926B2

公开(公告)日：2021-08-10

申请号：US16526710

申请日：2019-07-30

Applicant: Adobe Inc.

Inventor： Tulika Garg ,  Neeraj Goel

IPC: G06F16/583 ,  H04N1/387 ,  H04N5/262 ,  H04N1/393 ,  H04N5/232 ,  G06F3/0482 ,  G06F16/54 ,  G06T3/00 ,  G06T3/40 ,  G06T11/60

Abstract: Generating thumbnails from panoramic images is described. In one or more implementations, a 2D projection of a panoramic image is received and projected onto a 3D surface to generate a 3D projection. Portions of the 3D projection are formed, and each portion is projected to a 2D plane to generate 2D projections of the portions. Object recognition is then performed on the portions that identifies objects, attributes of the objects, and locations of the objects within the panoramic image. Responsive to an image search query matching one of the recognized objects, the system generates a thumbnail from the panoramic image specific to a portion of the panoramic image that contains the object and outputs the thumbnail.

公开(公告)号：US10521468B2

公开(公告)日：2019-12-31

申请号：US15621984

申请日：2017-06-13

Applicant: Adobe Inc.

Inventor： Tulika Garg ,  Neeraj Goel

IPC: G06F3/048 ,  G06F16/44 ,  G11B27/034 ,  G06F16/783 ,  G06F3/0481 ,  G06T3/00 ,  G06T15/04

Abstract: Generating animated seek previews for panoramic videos is described. In one or more implementations, a video frame associated with a seek point of a panoramic video is received. The video frame is reverse projected to generate a 3D projection. Portions of the 3D projection are then formed that are centered on and span an equatorial axis, and each portion is projected to a 2D plane to generate 2D projections of the portions. Animation frames are generated based on the projected portions, and the animation frames are compiled into an animation for consumption by a user as an animated seek preview of the video frame corresponding to the seek point.

公开(公告)号：US20190354550A1

公开(公告)日：2019-11-21

申请号：US16526710

申请日：2019-07-30

Applicant: Adobe Inc.

Inventor： Tulika Garg ,  Neeraj Goel

IPC: G06F16/583 ,  H04N1/387 ,  H04N5/262 ,  H04N1/393 ,  H04N5/232 ,  G06F3/0482 ,  G06F16/54 ,  G06T3/00 ,  G06T3/40

Abstract: Generating thumbnails from panoramic images is described. In one or more implementations, a 2D projection of a panoramic image is received and projected onto a 3D surface to generate a 3D projection. Portions of the 3D projection are formed, and each portion is projected to a 2D plane to generate 2D projections of the portions. Object recognition is then performed on the portions that identifies objects, attributes of the objects, and locations of the objects within the panoramic image. Responsive to an image search query matching one of the recognized objects, the system generates a thumbnail from the panoramic image specific to a portion of the panoramic image that contains the object and outputs the thumbnail.

公开(公告)号：US10791352B2

公开(公告)日：2020-09-29

申请号：US16427962

申请日：2019-05-31

Applicant: Adobe Inc.

Inventor： Angela Ranjeet ,  Kiran Chandra Zagabattuni ,  Pavan Kumar Bvn ,  Niraj Gupta ,  Neeraj Goel

IPC: H04N21/25 ,  H04N21/8549 ,  H04N21/466 ,  H04N21/234 ,  H04N21/258 ,  H04N21/45 ,  G11B27/031 ,  G11B27/034 ,  G11B27/036

Abstract: A dynamically created video preview can be provided to a viewer by stitching relevant video clips from a target video based on a viewer profile of the viewer. In various embodiments, a computer receives a request from a viewer to preview a video. The computer can then select one or more clips from the video based on the viewer profile of the viewer. Thereafter, the computer can generate a customized video preview from the one or more selected clips for the viewer based on the viewer profile. Other embodiments may be described and/or claimed.