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：US20210073612A1

公开(公告)日：2021-03-11

申请号：US16566797

申请日：2019-09-10

Applicant: NVIDIA Corporation

Inventor： Arash Vahdat ,  Arun Mohanray Mallya ,  Ming-Yu Liu ,  Jan Kautz

IPC: G06N3/04 ,  G06F7/57 ,  G06N3/063 ,  G06N3/08

Abstract: In at least one embodiment, differentiable neural architecture search and reinforcement learning are combined under one framework to discover network architectures with desired properties such as high accuracy, low latency, or both. In at least one embodiment, an objective function for search based on generalization error prevents the selection of architectures prone to overfitting.

公开(公告)号：US20210042503A1

公开(公告)日：2021-02-11

申请号：US17069478

申请日：2020-10-13

Applicant: NVIDIA Corporation

Inventor： Tero Tapani Karras ,  Samuli Matias Laine ,  David Patrick Luebke ,  Jaakko T. Lehtinen ,  Miika Samuli Aittala ,  Timo Oskari Aila ,  Ming-Yu Liu ,  Arun Mohanray Mallya ,  Ting-Chun Wang

IPC: G06K9/00 ,  G06T7/70 ,  G06N3/08

Abstract: A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.

公开(公告)号：US20240406405A1

公开(公告)日：2024-12-05

申请号：US18798466

申请日：2024-08-08

Applicant: Nvidia Corporation

Inventor： Aurobinda Maharana ,  Vignesh Ungrapalli ,  Ming-Yu Liu

IPC: H04N19/137 ,  H04N19/186 ,  H04N19/513

Abstract: Systems and methods herein address reference frame selection in video streaming applications using one or more processing units to identify a frame of a sequence of frames as a blurred frame based at least in part on a first variance of motion (VoM) of the frame being less than or equal to an adaptive threshold that is based in part on a moving average of variance of motion (MAoV) determined using one or more reference frames.

公开(公告)号：US20240114180A1

公开(公告)日：2024-04-04

申请号：US17955746

申请日：2022-09-29

Applicant: Nvidia Corporation

Inventor： Aurobinda Maharana ,  Vignesh Ungrapalli ,  Ming-Yu Liu

IPC: H04N21/231 ,  H04N19/136 ,  H04N19/154 ,  H04N19/172 ,  H04N19/423 ,  H04N19/70

CPC classification number: H04N21/23106 ,  H04N19/136 ,  H04N19/154 ,  H04N19/172 ,  H04N19/423 ,  H04N19/70

Abstract: Systems and methods herein address reference frame selection in video streaming applications using one or more processing units to replace, during receipt of an encoded video stream, a first set of frames stored in a cache with a second set of frames based at least in part on an indication within the encoded video stream that the second set of frames includes a non-blurred frame (NBF).

公开(公告)号：US20240054609A1

公开(公告)日：2024-02-15

申请号：US18195784

申请日：2023-05-10

Applicant: NVIDIA Corporation

Inventor： Xun Huang ,  Ming-Yu Liu

IPC: G06T5/50 ,  G06T7/10 ,  G06V10/82

CPC classification number: G06T5/50 ,  G06T7/10 ,  G06V10/82 ,  G06T2207/20221

Abstract: Apparatuses, systems, and techniques to generate images. In at least one embodiment, one or more neural networks are used to generate a panoramic image from a segmentation mask.

公开(公告)号：US20240020897A1

公开(公告)日：2024-01-18

申请号：US17862818

申请日：2022-07-12

Applicant: Nvidia Corporation

Inventor： Ting-Chun Wang ,  Ming-Yu Liu ,  Koki Nagano ,  Sameh Khamis ,  Jan Kautz

IPC: G06T11/60 ,  G06T5/00

CPC classification number: G06T11/60 ,  G06T5/006 ,  G06T2207/20084

Abstract: Apparatuses, systems, and techniques are presented to generate image data. In at least one embodiment, one or more neural networks are used to cause a lighting effect to be applied to one or more objects within one or more images based, at least in part, on synthetically generated images of the one or more objects.

公开(公告)号：US11775829B2

公开(公告)日：2023-10-03

申请号：US18079772

申请日：2022-12-12

Applicant: NVIDIA Corporation

Inventor： Tero Tapani Karras ,  Samuli Matias Laine ,  David Patrick Luebke ,  Jaakko T. Lehtinen ,  Miika Samuli Aittala ,  Timo Oskari Aila ,  Ming-Yu Liu ,  Arun Mohanray Mallya ,  Ting-Chun Wang

IPC: G06T9/00 ,  G06N3/08 ,  H04N19/20 ,  H04N7/15 ,  G06T7/73 ,  G06V40/16 ,  G06T5/00

CPC classification number: G06N3/08 ,  G06T5/003 ,  G06T7/73 ,  G06T9/002 ,  G06V40/168 ,  H04N7/157 ,  H04N19/20 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30201

Abstract: A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.

公开(公告)号：US20230229919A1

公开(公告)日：2023-07-20

申请号：US18186696

申请日：2023-03-20

Applicant: NVIDIA Corporation

Inventor： Amlan Kar ,  Aayush Prakash ,  Ming-Yu Liu ,  David Jesus Acuna Marrero ,  Antonio Torralba Barriuso ,  Sanja Fidler

IPC: G06N3/08 ,  G06F16/901 ,  G06T11/60 ,  G06N3/045 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G06V10/426

CPC classification number: G06N3/08 ,  G06F16/9024 ,  G06T11/60 ,  G06N3/045 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G06V10/426 ,  G06T2210/61

Abstract: In various examples, a generative model is used to synthesize datasets for use in training a downstream machine learning model to perform an associated task. The synthesized datasets may be generated by sampling a scene graph from a scene grammar—such as a probabilistic grammar— and applying the scene graph to the generative model to compute updated scene graphs more representative of object attribute distributions of real-world datasets. The downstream machine learning model may be validated against a real-world validation dataset, and the performance of the model on the real-world validation dataset may be used as an additional factor in further training or fine-tuning the generative model for generating the synthesized datasets specific to the task of the downstream machine learning model.

公开(公告)号：US20230147641A1

公开(公告)日：2023-05-11

申请号：US17522776

申请日：2021-11-09

Applicant: Nvidia Corporation

Inventor： Ting-Chun Wang ,  Tim Brooks ,  Ming-Yu Liu ,  Tero Karras ,  Jaakko Lehtinen

IPC: G06T13/00 ,  G06N3/04

CPC classification number: G06T13/00 ,  G06N3/0454

Abstract: Apparatuses, systems, and techniques are presented to reconstruct one or more images. In at least one embodiment, one or more neural networks are used to generate one or more images of one or more objects based, at least in part, on input indicating motion of the one or more objects.