-
公开(公告)号:US20220114702A1
公开(公告)日:2022-04-14
申请号:US17406902
申请日:2021-08-19
Applicant: Nvidia Corporation
Inventor: Shiqiu Liu , Robert Pottorff , Guilin Liu , Karan Sapra , Jon Barker , David Tarjan , Pekka Janis , Edvard Fagerholm , Lei Yang , Kevin Jonathan Shih , Marco Salvi , Timo Roman , Andrew Tao , Bryan Catanzaro
Abstract: Apparatuses, systems, and techniques are presented to generate images. In at least one embodiment, one or more neural networks are used to generate one or more images using one or more pixel weights.
-
公开(公告)号:US20220114701A1
公开(公告)日:2022-04-14
申请号:US17172330
申请日:2021-02-10
Applicant: Nvidia Corporation
Inventor: Shiqiu Liu , Robert Pottorff , Guilin Liu , Karan Sapra , Jon Barker , David Tarjan , Pekka Janis , Edvard Fagerholm , Lei Yang , Kevin Shih , Marco Salvi , Timo Roman , Andrew Tao , Bryan Catanzaro
Abstract: Apparatuses, systems, and techniques are presented to generate images. In at least one embodiment, one or more neural networks are used to generate one or more images using one or more pixel weights determined based, at least in part, on one or more sub-pixel offset values.
-
公开(公告)号:US20240104692A1
公开(公告)日:2024-03-28
申请号:US18106963
申请日:2023-02-07
Applicant: NVIDIA Corporation
Inventor: Robert Thomas Pottorff , Karan Sapra , Andrew Leighton Edelsten
CPC classification number: G06T3/4046 , G06T1/20 , G06T3/4007
Abstract: Apparatuses, systems, and techniques to process image frames. In at least one embodiment, an application programming interface (API) is performed to indicate support to use one or more neural networks to perform frame interpolation.
-
公开(公告)号:US20240104690A1
公开(公告)日:2024-03-28
申请号:US18106971
申请日:2023-02-07
Applicant: NVIDIA Corporation
Inventor: Robert Thomas Pottorff , Karan Sapra , Andrew Leighton Edelsten
IPC: G06T3/40
CPC classification number: G06T3/4007 , G06T3/4046
Abstract: Apparatuses, systems, and techniques to process image frames. In at least one embodiment, an application programming interface (API) is performed to indicate frame size information using one or more neural networks.
-
公开(公告)号:US20240098216A1
公开(公告)日:2024-03-21
申请号:US17949153
申请日:2022-09-20
Applicant: NVIDIA Corporation
Inventor: Robert Thomas Pottorff , Karan Sapra , Zhekun Luo , Andrew J. Tao , Bryan Christopher Catanzaro
CPC classification number: H04N7/014 , G06T5/50 , G06T7/20 , G06T7/579 , G06T7/70 , G06V10/82 , H04N19/132 , G06T2207/10016 , G06T2207/20221
Abstract: Apparatuses, systems, and techniques to process image frames. In at least one embodiment, one or more neural networks are used to blend two or more video frames between a first video frame and a second video frame. In at least one embodiment, a blended video frame is used to generate an intermediate video frame between the first video frame and the second video frame.
-
公开(公告)号:US20230186428A1
公开(公告)日:2023-06-15
申请号:US18106348
申请日:2023-02-06
Applicant: NVIDIA Corporation
Inventor: Guilin Liu , Andrew Tao , Bryan Christopher Catanzaro , Ting-Chun Wang , Zhiding Yu , Shiqiu Liu , Fitsum Reda , Karan Sapra , Brandon Rowlett
CPC classification number: G06T3/4038 , G06T3/4046 , G06T7/40 , G06N3/08 , G06V10/776 , G06V10/82 , G06V10/454 , G06V10/54 , G06T2207/20081 , G06T2207/20084
Abstract: Apparatuses, systems, and techniques for texture synthesis from small input textures in images using convolutional neural networks. In at least one embodiment, one or more convolutional layers are used in conjunction with one or more transposed convolution operations to generate a large textured output image from a small input textured image while preserving global features and texture, according to various novel techniques described herein.
-
公开(公告)号:US20220038653A1
公开(公告)日:2022-02-03
申请号:US16944066
申请日:2020-07-30
Applicant: NVIDIA Corporation
Inventor: Fitsum Reda , Karan Sapra , Robert Thomas Pottorff , Shiqiu Liu , Andrew Tao , Bryan Christopher Catanzaro
IPC: H04N7/01
Abstract: Apparatuses, systems, and techniques to generate interpolated video frames. In at least one embodiment, an interpolated video frame is generated based, at least in part, on one of a plurality of possible motions of one or more objects from a first video frame to a second video frame.
-
-
-
-
-
-