公开(公告)号：US12256098B1

公开(公告)日：2025-03-18

申请号：US17691691

申请日：2022-03-10

Applicant: Apple Inc.

Inventor： Khaled Mammou ,  Afshin Taghavi Nasrabadi ,  Maneli Noorkami ,  Fabrice A. Robinet

IPC: H04N19/597 ,  G06T17/20 ,  H04N19/176 ,  H04N19/182

Abstract: A decoding computing device receives a bit stream for compressed 3D volumetric content. The bit stream includes video encoded image frames comprising packed attribute patch images and depth maps for the 3D volumetric content. Instead of generating a mesh having a vertex for each depth value signaled in the depth map, the decoder performs a real-time mesh simplification process to reduce a resolution of the mesh, such that the mesh resolution is reduced without exceeding an error threshold, which may be dynamically determined. Additionally, the decoder may perform a re-meshing of particular regions of the mesh for the 3D volumetric content to avoid cracks or gaps.

公开(公告)号：US12219118B1

公开(公告)日：2025-02-04

申请号：US17678815

申请日：2022-02-23

Applicant: Apple Inc.

Inventor： Afshin Taghavi Nasrabadi ,  Maneli Noorkami

IPC: H04N13/25 ,  G06T15/00 ,  G06T19/00 ,  G06T19/20

Abstract: In one implementation, a camera rig comprises: a first array of image sensors arranged in a planar configuration, wherein the first array of image sensors is provided to capture a first image stream from a first perspective of a physical environment; a second array of image sensors arranged in a non-planar configuration, wherein the second array of image sensors is provided to capture a second image stream from a second perspective of the physical environment different from the first perspective; a buffer provided to store the first and second image streams; and an image processing engine provided to generate a 3D reconstruction of the physical environment based on the first and second image streams.

公开(公告)号：US11418769B1

公开(公告)日：2022-08-16

申请号：US17222872

申请日：2021-04-05

Applicant: Apple Inc.

Inventor： Afshin Taghavi Nasrabadi ,  Maneli Noorkami ,  Ranjit Desai

IPC: H04N13/117 ,  G06T15/08 ,  H04N13/161 ,  H04N13/178

Abstract: A system comprises an encoder configured to compress and encode data for three-dimensional volumetric content. The encoder also is configured to segment the three-dimensional volumetric content based on viewing areas, wherein different ones of the viewing areas correspond to visible portions of the volumetric content. The system may provide metadata to a client device to support viewport adaptive rendering of the three-dimensional volumetric content or may adaptively stream portions of the three-dimensional volumetric content to a rending device based on viewing areas of the three-dimensional volumetric content that are to be rendered at the rendering device.

公开(公告)号：US20240406364A1

公开(公告)日：2024-12-05

申请号：US18644222

申请日：2024-04-24

Applicant: Apple Inc.

Inventor： Maneli Noorkami ,  Afshin Taghavi Nasrabadi ,  Alexander P. Yu ,  Michael A. Glass ,  Travis W. Brown

IPC: H04N13/189 ,  H04N13/156 ,  H04N13/178 ,  H04N13/366

Abstract: A head-mounted device is provided that includes a variety of subsystems for generating extended reality content, displaying the extended reality content, and recording the extended reality content. The device may include a graphics rendering pipeline configured to render virtual content, tracking sensors configured to obtain user tracking information, a virtual content compositor configured to composite virtual frames based on the virtual content and the user tracking information, cameras configured to capture a video feed, a media merging compositor configured to overlay the composited virtual frames and the video feed, and a recording pipeline configured to record parameters, metadata, raw content, and/or adjusted content in an extended reality recording file. The extended reality recording file may have multiple discrete portions that may each be individually edited. The extended reality recording file may be used to present a replay on the head-mounted device and/or may be exported to an external device.

公开(公告)号：US11948338B1

公开(公告)日：2024-04-02

申请号：US17691754

申请日：2022-03-10

Applicant: Apple Inc.

Inventor： Khaled Mammou ,  Fabrice A. Robinet ,  Maneli Noorkami ,  Afshin Taghavi Nasrabadi

IPC: G06T9/00 ,  G06T3/40 ,  G06T3/4023 ,  G06T15/10 ,  G06T17/20

CPC classification number: G06T9/001 ,  G06T3/4023 ,  G06T15/10 ,  G06T17/205 ,  G06T2200/04 ,  G06T2200/08 ,  G06T2210/08

Abstract: An encoder encodes three-dimensional (3D) volumetric content, such as immersive media, using video encoded attribute patch images packed into a 2D atlas to communicate the attribute values for the 3D volumetric content. The encoder also uses mesh-encoded sub-meshes to communicate geometry information for portions of the 3D object or scene corresponding to the attribute patch images packed into the 2D atlas. The encoder applies decimation operations to the sub-meshes to simplify the sub-meshes before mesh encoding the sub-meshes. A distortion analysis is performed to bound the level to which the sub-meshes are simplified at the encoder. Mesh simplification at the encoder reduces the number of vertices and edges included in the sub-meshes which simplifies rendering at a decoder receiving the encoded 3D volumetric content.

公开(公告)号：US11861788B1

公开(公告)日：2024-01-02

申请号：US17347404

申请日：2021-06-14

Applicant: Apple Inc.

Inventor： Afshin Taghavi Nasrabadi ,  Maneli Noorkami

IPC: G06T15/08 ,  G06T7/50 ,  G06T9/00

CPC classification number: G06T15/08 ,  G06T7/50 ,  G06T9/00 ,  G06T2207/10016

Abstract: One or more computing devices implement a mesh analysis for evaluating meshes to be rendered when rendering immersive content. The mesh analysis identifies objects in a three-dimensional scene and determines geometrical complexity values for the objects. Objects with similar geometrical complexities are grouped into areas and a mesh vertices budget is determined for the respective areas. Metadata indicating the area definitions and corresponding mesh vertices budgets are generated. The metadata may be uploaded to a server to simplify meshes in the scene prior to streaming to a client, or the metadata may be provided to a client for use in simplifying the meshes as part of rendering the scene.