公开(公告)号：US20200045289A1

公开(公告)日：2020-02-06

申请号：US16050285

申请日：2018-07-31

Applicant: Intel Corporation

Inventor： Ben Raziel ,  Asaf Shiloni ,  Gilad Bauman ,  Jill Boyce ,  Tzach Ashkenazi ,  Ilan Beer ,  Eytan Kats

IPC: H04N13/156 ,  H04N13/332 ,  H04N13/161 ,  G06N3/08 ,  G06N5/04 ,  G06N99/00

Abstract: Embodiments are generally directed to neural network based patch blending for immersive video. An embodiment of a system includes one or more processor cores; a memory to store data for images in immersive video; and a neural network training framework. The neural network training framework is to generate a trained neural network for blending of a view of an object with patches generated for one or more detected occlusions for the object.

公开(公告)号：US11250616B2

公开(公告)日：2022-02-15

申请号：US16832466

申请日：2020-03-27

Applicant: Intel Corporation

Inventor： Adam Kaplan ,  Yuval Hovers ,  Ilan Beer ,  Ben Raziel

IPC: G06T7/194 ,  G06T15/00 ,  G06T15/08 ,  G06T15/20 ,  H04N9/31

Abstract: Methods, systems and apparatuses may provide for technology that generates a point cloud model of an object depicted in image content associated with a plurality of physical cameras, generates a color projection of the point cloud model based on viewpoint information associated with a virtual camera, and excludes background color information from the color projection based on one or more segmentation masks associated with the object. The technology may also exclude peripheral information from the color projection based on at least one of the segmentation mask(s) and the viewpoint information.

公开(公告)号：US20210304490A1

公开(公告)日：2021-09-30

申请号：US16832466

申请日：2020-03-27

Applicant: Intel Corporation

Inventor： Adam Kaplan ,  Yuval Hovers ,  Ilan Beer ,  Ben Raziel

IPC: G06T15/08 ,  H04N9/31 ,  G06T7/194

Abstract: Methods, systems and apparatuses may provide for technology that generates a point cloud model of an object depicted in image content associated with a plurality of physical cameras, generates a color projection of the point cloud model based on viewpoint information associated with a virtual camera, and excludes background color information from the color projection based on one or more segmentation masks associated with the object. The technology may also exclude peripheral information from the color projection based on at least one of the segmentation mask(s) and the viewpoint information.

公开(公告)号：US10819968B2

公开(公告)日：2020-10-27

申请号：US16050285

申请日：2018-07-31

Applicant: Intel Corporation

Inventor： Ben Raziel ,  Asaf Shiloni ,  Gilad Bauman ,  Jill Boyce ,  Tzach Ashkenazi ,  Ilan Beer ,  Eytan Kats

IPC: H04N13/156 ,  H04N13/332 ,  G06N3/08 ,  G06N5/04 ,  H04N13/161 ,  G06N20/00

Abstract: Embodiments are generally directed to neural network based patch blending for immersive video. An embodiment of a system includes one or more processor cores; a memory to store data for images in immersive video; and a neural network training framework. The neural network training framework is to generate a trained neural network for blending of a view of an object with patches generated for one or more detected occlusions for the object.

公开(公告)号：US20200045344A1

公开(公告)日：2020-02-06

申请号：US16050509

申请日：2018-07-31

Applicant: Intel Corporation

Inventor： Jill Boyce ,  Atsuo Kuwahara ,  Tzach Ashkenazi ,  Ilan Beer ,  Eytan Kats ,  Prasoonkumar Surti ,  Kai Xiao ,  Jeffrey Tripp ,  Narayan Biswal ,  Jason Tanner ,  Nilesh Shah ,  Yi-Jen Chiu ,  Mayuresh M. Varerkar ,  Maria Bortman ,  Jonathan Distler ,  Itay Kaufman

IPC: H04N19/90 ,  G06T15/50 ,  G06T7/557 ,  H04N21/218 ,  G06T1/20 ,  G06T19/00

Abstract: An apparatus to facilitate processing video bit stream data is disclosed. The apparatus includes one or more processors to receive point cloud data included in the video bit stream data to be projected into two or more angles and encode multiple projections for a point cloud point upon a determination that the point cloud point will be included in patches in two or more of the multiple projections.