公开(公告)号：US11902705B2

公开(公告)日：2024-02-13

申请号：US16558620

申请日：2019-09-03

Applicant: Nvidia Corporation

Inventor： Kevin Shih ,  Aysegul Dundar ,  Animesh Garg ,  Robert Pottorff ,  Andrew Tao ,  Bryan Catanzaro

IPC: G06N3/04 ,  H04N7/01 ,  G06N3/08 ,  G06F18/214 ,  G06F18/21 ,  G06N3/044 ,  G06N3/045

CPC classification number: H04N7/0135 ,  G06F18/214 ,  G06F18/217 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08

Abstract: Apparatuses, systems, and techniques to enhance video are disclosed. In at least one embodiment, one or more neural networks are used to create, from a first video, a second video having one or more additional video frames.

公开(公告)号：US20220101494A1

公开(公告)日：2022-03-31

申请号：US17039805

申请日：2020-09-30

Applicant: NVIDIA Corporation

Inventor： Morteza Mardani Korani ,  Guilin Liu ,  Aysegul Dundar ,  Shiqiu Liu ,  Andrew J. Tao ,  Bryan Christopher Catanzaro

IPC: G06T3/40 ,  G06K9/62

Abstract: Apparatuses, systems, and techniques to scale textured images using a Fourier transform in conjunction with one or more neural networks. In at least one embodiment, a neural network generates an expanded image from an input image by applying a Fourier transform to one or more feature maps generated by said neural network and up-scaling one or more resulting frequency domain feature maps before generating an expanded output image based on up-scaled feature maps.

公开(公告)号：US20210064925A1

公开(公告)日：2021-03-04

申请号：US16558620

申请日：2019-09-03

Applicant: Nvidia Corporation

Inventor： Kevin Shih ,  Aysegul Dundar ,  Animesh Garg ,  Robert Pottorff ,  Andrew Tao ,  Bryan Catanzaro

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: Apparatuses, systems, and techniques to enhance video are disclosed. In at least one embodiment, one or more neural networks are used to create, from a first video, a second video having one or more additional video frames.

公开(公告)号：US10984286B2

公开(公告)日：2021-04-20

申请号：US16265725

申请日：2019-02-01

Applicant: NVIDIA Corporation

Inventor： Aysegul Dundar ,  Ming-Yu Liu ,  Ting-Chun Wang ,  John Zedlewski ,  Jan Kautz

IPC: G06K9/62 ,  G06K9/32 ,  G06K9/00 ,  G01N3/08 ,  G06N3/04 ,  G06T7/10 ,  G06T3/00 ,  G06T11/00 ,  G06T15/00 ,  G06N3/08

Abstract: A style transfer neural network may be used to generate stylized synthetic images, where real images provide the style (e.g., seasons, weather, lighting) for transfer to synthetic images. The stylized synthetic images may then be used to train a recognition neural network. In turn, the trained neural network may be used to predict semantic labels for the real images, providing recognition data for the real images. Finally, the real training dataset (real images and predicted recognition data) and the synthetic training dataset are used by the style transfer neural network to generate stylized synthetic images. The training of the neural network, prediction of recognition data for the real images, and stylizing of the synthetic images may be repeated for a number of iterations. The stylization operation more closely aligns a covariate of the synthetic images to the covariate of the real images, improving accuracy of the recognition neural network.

公开(公告)号：US20220180528A1

公开(公告)日：2022-06-09

申请号：US17678666

申请日：2022-02-23

Applicant: NVIDIA Corporation

Inventor： Aysegul Dundar ,  Kevin Jonathan Shih ,  Animesh Garg ,  Robert Thomas Pottorff ,  Andrew Tao ,  Bryan Christopher Catanzaro

IPC: G06T7/194 ,  G06N20/00 ,  G06N5/04 ,  G06T7/70 ,  G06N3/08 ,  G06V20/20

Abstract: Apparatuses, systems, and techniques to perform unsupervised keypoint or landmark learning using one or more neural networks. In at least one embodiment, one or more neural networks use pose and appearance information to construct a foreground and a background, which are then used to reconstruct an input image and determine loss values to train the one or more neural networks.

公开(公告)号：US20210067735A1

公开(公告)日：2021-03-04

申请号：US16559312

申请日：2019-09-03

Applicant: Nvidia Corporation

Inventor： Fitsum Reda ,  Deqing Sun ,  Aysegul Dundar ,  Mohammad Shoeybi ,  Guilin Liu ,  Kevin Shih ,  Andrew Tao ,  Jan Kautz ,  Bryan Catanzaro

IPC: H04N7/01 ,  G06N3/04 ,  G06N3/08

Abstract: Apparatuses, systems, and techniques to enhance video. In at least one embodiment, one or more neural networks are used to create, from a first video, a second video having a higher frame rate, higher resolution, or reduced number of missing or corrupt video frames.

公开(公告)号：US20190244060A1

公开(公告)日：2019-08-08

申请号：US16265725

申请日：2019-02-01

Applicant: NVIDIA Corporation

Inventor： Aysegul Dundar ,  Ming-Yu Liu ,  Ting-Chun Wang ,  John Zedlewski ,  Jan Kautz

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06K9/32 ,  G06T3/00 ,  G06T7/10

CPC classification number: G06K9/6256 ,  G06K9/3233 ,  G06K9/6267 ,  G06N3/0454 ,  G06N3/08 ,  G06T3/0056 ,  G06T7/10

Abstract: A style transfer neural network may be used to generate stylized synthetic images, where real images provide the style (e.g., seasons, weather, lighting) for transfer to synthetic images. The stylized synthetic images may then be used to train a recognition neural network. In turn, the trained neural network may be used to predict semantic labels for the real images, providing recognition data for the real images. Finally, the real training dataset (real images and predicted recognition data) and the synthetic training dataset are used by the style transfer neural network to generate stylized synthetic images. The training of the neural network, prediction of recognition data for the real images, and stylizing of the synthetic images may be repeated for a number of iterations. The stylization operation more closely aligns a covariate of the synthetic images to the covariate of the real images, improving accuracy of the recognition neural network.