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：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：US11113819B2

公开(公告)日：2021-09-07

申请号：US16248135

申请日：2019-01-15

Applicant: NVIDIA Corporation

Inventor： Vukasin Milovanovic ,  Joy D'Souza ,  Rochelle Pereira ,  Jianyuan Min

IPC: G06T7/13 ,  G06T19/00 ,  G06T7/73

Abstract: In various examples, image data may be received that represents an image. Corner detection may be used to identify pixels that may be candidate corner points. The image data may be converted from a higher dimensional color space to a converted image in a lower dimensional color space, and boundaries may be identified within the converted image. A set of the candidate corner points may be determined that are within a threshold distance to one of the boundaries, and the set of the candidate corner points may be analyzed to determine a subset of the candidate corner points representative of corners of polygons. Using the subset of the candidate corner points, one or more polygons may be identified, and a filter may be applied to the polygons to identify a polygon as corresponding to a fiducial marker boundary of a fiducial marker.

公开(公告)号：US20220374714A1

公开(公告)日：2022-11-24

申请号：US17324452

申请日：2021-05-19

Applicant: Nvidia Corporation

Inventor： Nandita Miyar Nayak ,  Akarsh Zingade ,  Jianyuan Min ,  Rochelle Pereira

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62 ,  G06T1/20 ,  G06T5/50

Abstract: Real time content enhancement can be provided using a solution that is lightweight enough to operate on client devices, even for high resolution, high bitrate content. An enhancement process can include a neural network that upscales the content to a target resolution while also enhancing a visual quality of the content, such as to sharpen visual aspects of the content and reduce a presence of artifacts. Such an approach can enable compressed content to be transmitted in streams across a network, in order to conserve bandwidth and data transmission, while also enabling that content to be upscaled and enhanced at the client device in real time, such that a user or viewer can experience the content at, near, or above its intended or original visual quality.

公开(公告)号：US20210366124A1

公开(公告)日：2021-11-25

申请号：US17393615

申请日：2021-08-04

Applicant: NVIDIA Corporation

Inventor： Vukasin Milovanovic ,  Joy D'Souza ,  Rochelle Pereira ,  Jianyuan Min

IPC: G06T7/13 ,  G06T19/00 ,  G06T7/73

Abstract: In various examples, image data may be received that represents an image. Corner detection may be used to identify pixels that may be candidate corner points. The image data may be converted from a higher dimensional color space to a converted image in a lower dimensional color space, and boundaries may be identified within the converted image. A set of the candidate corner points may be determined that are within a threshold distance to one of the boundaries, and the set of the candidate corner points may be analyzed to determine a subset of the candidate corner points representative of corners of polygons. Using the subset of the candidate corner points, one or more polygons may be identified, and a filter may be applied to the polygons to identify a polygon as corresponding to a fiducial marker boundary of a fiducial marker.

公开(公告)号：US20200226762A1

公开(公告)日：2020-07-16

申请号：US16248135

申请日：2019-01-15

Applicant: NVIDIA Corporation

Inventor： Vukasin Milovanovic ,  Joy D'Souza ,  Rochelle Pereira ,  Jianyuan Min

IPC: G06T7/13 ,  G06T19/00 ,  G06T7/73

Abstract: In various examples, image data may be received that represents an image. Corner detection may be used to identify pixels that may be candidate corner points. The image data may be converted from a higher dimensional color space to a converted image in a lower dimensional color space, and boundaries may be identified within the converted image. A set of the candidate corner points may be determined that are within a threshold distance to one of the boundaries, and the set of the candidate corner points may be analyzed to determine a subset of the candidate corner points representative of corners of polygons. Using the subset of the candidate corner points, one or more polygons may be identified, and a filter may be applied to the polygons to identify a polygon as corresponding to a fiducial marker boundary of a fiducial marker.

公开(公告)号：US20250069191A1

公开(公告)日：2025-02-27

申请号：US18452634

申请日：2023-08-21

Applicant: NVIDIA Corporation

Inventor： Iuri Frosio ,  Mayoore Selvarasa Jaiswal ,  Jan Kautz ,  Jianyuan Min

IPC: G06T5/50 ,  H04N23/743

Abstract: Systems and methods are disclosed related to synthetic bracketing for exposure correction. A deep learning based method and system produces a set of differently exposed images from a single input image. The images in the set may be combined to produce an output image with improved global and local exposure compared with the input image. An image encoder applies learned parameters to each input image to generate a set of image features including local exposure estimates for each of two or more regions of the input image and a low resolution latent representation of the input image. A decoder receives the local exposure estimates, the latent representation, and target enhancements that are processed to generate synthesized transformations. When applied to the input image, the synthesized transformations produce the set of transformed images. Each transformed image is a version of the input image synthesized to correspond to a respective target enhancement.

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.