公开(公告)号：US20230368432A1

公开(公告)日：2023-11-16

申请号：US18359126

申请日：2023-07-26

Applicant: Apple Inc.

Inventor： Felipe Bacim De Araujo E Silva ,  Dan C. Lelescu ,  Sebastien Eric Gilles Leprince ,  Gary L Vondran, JR.

IPC: G06T11/00 ,  G06T7/55 ,  G06T3/00

CPC classification number: G06T11/00 ,  G06T7/55 ,  G06T3/00 ,  G06T2207/20212

Abstract: Novel viewpoints may be rendered using arrays of camera images with synthesized viewpoints. Different viewpoints of a scene may be captured via image sensors. Depth information may be determined for the captured viewpoints. An array of images may be generated that includes synthetic viewpoints generated from the captured viewpoints and depth information. A request to render a novel viewpoint may be received. Then novel viewpoint may be rendered using the array of images with synthetic viewpoints.

公开(公告)号：US12039632B2

公开(公告)日：2024-07-16

申请号：US18359126

申请日：2023-07-26

Applicant: Apple Inc.

Inventor： Felipe Bacim De Araujo E Silva ,  Dan C. Lelescu ,  Sebastien Eric Gilles Leprince ,  Gary L Vondran, Jr.

IPC: G06T11/00 ,  G06T3/00 ,  G06T7/55

CPC classification number: G06T11/00 ,  G06T3/00 ,  G06T7/55 ,  G06T2207/20212

Abstract: Novel viewpoints may be rendered using arrays of camera images with synthesized viewpoints. Different viewpoints of a scene may be captured via image sensors. Depth information may be determined for the captured viewpoints. An array of images may be generated that includes synthetic viewpoints generated from the captured viewpoints and depth information. A request to render a novel viewpoint may be received. Then novel viewpoint may be rendered using the array of images with synthetic viewpoints.

公开(公告)号：US12015758B1

公开(公告)日：2024-06-18

申请号：US17539524

申请日：2021-12-01

Applicant: Apple Inc.

Inventor： Gary L. Vondran, Jr. ,  Dan C. Lelescu ,  Robert K. Molholm ,  Nicolas V. Scapel ,  Kathrin Berkner-Cieslicki ,  Seung Wook Kim

IPC: H04N13/279 ,  H04N13/25 ,  H04N13/282 ,  H04N13/31 ,  H04N13/344

CPC classification number: H04N13/279 ,  H04N13/25 ,  H04N13/282 ,  H04N13/31 ,  H04N13/344

Abstract: Various implementations disclosed herein include devices, systems, and methods that provide images for displaying a 3D appearance of a tracked object on a view dependent device. In some implementations, a set of multiple images of the object from different capture positions is provided and then adjusted such as to render the object in focus when using the adjusted images for display on the view dependent device. In some implementations, the set of multiple images is provided that includes virtual images generated using virtual image sensors that may improve the appearance of out of focus regions (e.g., outside the 3D object appearance) on the view dependent device. In some implementations, the set of multiple images of a person provides a hologram of the person (e.g., left and right eye views provide the appearance of a 3D person) where the images are adjusted to improve gaze direction of eyes of the person.

公开(公告)号：US20240107162A1

公开(公告)日：2024-03-28

申请号：US18347604

申请日：2023-07-06

Applicant: Apple Inc.

Inventor： Dan C. Lelescu ,  Rohit Rajiv Ranade ,  Noah Bedard ,  Brian McCall ,  Kathrin Berkner Cieslicki ,  Michael W. Tao ,  Robert K. Molholm ,  Toke Jansen ,  Vladimir Krneta

IPC: H04N23/67 ,  G06T7/30 ,  H04N23/958

CPC classification number: H04N23/67 ,  G06T7/30 ,  H04N23/958 ,  G06T2207/20084

Abstract: A method for image enhancement includes capturing multiple input images of a scene, including at least a first input image having a first field of view (FOV) captured with a first focal depth and a second input image having a second FOV captured with a second focal depth. The input images in the sequence are preprocessed so as to align the images. The aligned images are processed in a neural network, which generates an output image having an extended depth of field encompassing at least the first and second focal depths.