公开(公告)号：US20220237735A1

公开(公告)日：2022-07-28

申请号：US17159887

申请日：2021-01-27

Applicant: NVIDIA Corporation

Inventor： Akarsh Umesh Zingade ,  Jianyuan Min ,  Shuye Han ,  Rochelle Pereira

IPC: G06T3/40 ,  G06K9/00 ,  H04N7/15

Abstract: Systems, processes, and techniques to automatically detect and enlarge a speaking one of plurality of participants on one side of a video conference. In at least one embodiment, the speaking participant is identified using one or more heuristics and/or one or more neural networks.

公开(公告)号：US11748845B2

公开(公告)日：2023-09-05

申请号：US17159887

申请日：2021-01-27

Applicant: NVIDIA Corporation

Inventor： Akarsh Umesh Zingade ,  Jianyuan Min ,  Shuye Han ,  Rochelle Pereira

IPC: G06T3/40 ,  H04N7/15 ,  G06V20/40 ,  G06V40/16

CPC classification number: G06T3/4038 ,  G06V20/40 ,  G06V40/171 ,  H04N7/15 ,  G06T2200/32

Abstract: Systems, processes, and techniques to automatically detect and enlarge a speaking one of plurality of participants on one side of a video conference. In at least one embodiment, the speaking participant is identified using one or more heuristics and/or one or more neural networks.

公开(公告)号：US20250061729A1

公开(公告)日：2025-02-20

申请号：US18238335

申请日：2023-08-25

Applicant: NVIDIA Corporation

Inventor： Prash Goel ,  Umar Iqbal ,  Akarsh Umesh Zingade ,  Pavlo Molchanov

IPC: G06V20/64 ,  G06T7/174 ,  G06T7/70 ,  G06V10/26 ,  G06V10/82

Abstract: Apparatuses, systems, and techniques to identify three-dimensional positions of partially occluded objects in images. In at least one embodiment, one or more neural networks identify the three-dimensional positions of occluded portions of objects in a first image based, at least in part, on one or more second images including non-occluded objects.

公开(公告)号：US20230394627A1

公开(公告)日：2023-12-07

申请号：US18236202

申请日：2023-08-21

Applicant: NVIDIA Corporation

Inventor： Akarsh Umesh Zingade ,  Jianyuan Min ,  Shuye Han ,  Rochelle Pereira

IPC: G06T3/40 ,  H04N7/15 ,  G06V20/40 ,  G06V40/16

CPC classification number: G06T3/4038 ,  H04N7/15 ,  G06V20/40 ,  G06V40/171 ,  G06T2200/32

Abstract: Systems, processes, and techniques to automatically detect and enlarge a speaking one of plurality of participants on one side of a video conference. In at least one embodiment, the speaking participant is identified using one or more heuristics and/or one or more neural networks.