-
公开(公告)号：US11574155B2
公开(公告)日：2023-02-07
申请号：US17226561
申请日：2021-04-09
Applicant: Nvidia Corporation
Inventor： Aayush Prakash , Shoubhik Debnath , Jean-Francois Lafleche , Eric Cameracci , Gavriel State , Marc Teva Law
Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
-
2.发明公开公开(公告)号：US20240312122A1
公开(公告)日：2024-09-19
申请号：US18184459
申请日：2023-03-15
Applicant: Nvidia Corporation
Inventor： Nicolas Moenne-Loccoz , Zan Gojcic , Gavriel State , Zian Wang , Ignacio Llamas
CPC classification number: G06T15/506 , G06T5/50 , G06V10/60 , G06V10/761 , G06V10/82 , G06T2207/20221
Abstract: Approaches presented herein provide for the generation of visual content, including different types of content representations from different sources, rendered to include consistent scene illumination for the various representations. A first render pass can produce a first image including only proxies of implicit representations (e.g., NeRF objects) under scene illumination. A second render pass can produce a second image that includes a representation of the explicit scene objects, as well as the proxies of the implicit representations, under the scene illumination, which produces secondary lighting effects. The first and second images are compared to determine irradiance ratio data for the various pixel locations. A third render pass can produce a third image that includes the implicit representations, which can have relighting performed according to the irradiance ratio data to include the secondary lighting effects. The implicit and explicit objects can then be composited to produce an image with consistent scene illumination.
-
公开(公告)号：US20220230376A1
公开(公告)日：2022-07-21
申请号：US17611763
申请日：2020-05-15
Applicant: Nvidia Corporation
Inventor： Artem Rozantsev , Marco Foco , Gavriel State
Abstract: Animation can be generated with a high perceptive quality by utilizing a trained neural network that takes as input a current state of a virtual character to be animated and predict how this character would appear in one or more subsequent frames. Such a process can be performed recursively to generate the data for these frames. During training, each frame of a generated sequence can be predicted from a result for a previous frame, and this generated sequence can be compared with a ground truth sequence using a generative network. Differences between the ground truth and generated animation sequences can be minimized, whereby a specific objective function does not need to be manually defined. Minimizing differences between the generated animation sequences and ground truth sequences during training improves the quality of network predictions for single frames at inference time.
-
4.发明公开公开(公告)号：US20240221288A1
公开(公告)日：2024-07-04
申请号：US18147426
申请日：2022-12-28
Applicant: Nvidia Corporation
Inventor： Marco Foco , Michael Kass , Gavriel State , Artem Rozantsev
IPC: G06T15/20 , G06T7/55 , G06T11/00 , G06V10/764
CPC classification number: G06T15/205 , G06T7/55 , G06T11/001 , G06V10/764 , G06T2207/20081
Abstract: Approaches presented herein provide for automatic generation of representative two-dimensional (2D) images for three-dimensional (3D) objects or assets. In generating these 2D images, a set of options is determined such as may relate to viewpoint or other parameters of a virtual camera. A set of sample points is determined from which to generate 2D images of a 3D model, for example, with 2D images being processed using a classifier to determine which of these images generates a classification with highest confidence or probability, individually or with respect to other classifications. The sample point for this selected image can then be used to select nearby sample points as part of a refinement or optimization process, where 2D images can again be generated and processed using a classifier to identify a 2D image with highest classification probability or confidence, which can be selected as representative of the 3D object or asset.
-
Patent Agency Ranking
5.发明公开公开(公告)号：US20240203052A1
公开(公告)日：2024-06-20
申请号：US18066135
申请日：2022-12-14
Applicant: Nvidia Corporation
Inventor： Marco Foco , András Bódis-Szomorú , Isaac Deutsch , Artem Rozantsev , Michael Shelley , Gavriel State , Jiehan Wang , Anita Hu , Jean-Francois Lafleche
CPC classification number: G06T17/20 , G06T7/33 , G06V10/82 , G06V2201/07
Abstract: Approaches presented herein can provide for the automatic generation of a digital representation of an environment that may include multiple objects of various object types. An initial representation (e.g., a point cloud) of the environment can be generated from registered image or scan data, for example, and objects in the environment can be segmented and identified based at least on that initial representation. For objects that are recognized based on these segmentations, stored accurate representations can be substituted for those objects in the representation of the environment, and if no such model is available then a mesh or other representation of that object can be generated and positioned in the environment. A result can then include a 3D representation of a scene or environment in which objects are identified and segmented as individual objects, and representations of the scene or environment can be viewed, and interacted with, through various viewports, positions, and perspectives.
-
公开(公告)号：US20210374489A1
公开(公告)日：2021-12-02
申请号：US17226561
申请日：2021-04-09
Applicant: Nvidia Corporation
Inventor： Aayush Prakash , Shoubhik Debnath , Jean-Francois Lafleche , Eric Cameracci , Gavriel State , Marc Teva Law
Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
-
公开(公告)号：US20240320993A1
公开(公告)日：2024-09-26
申请号：US18673785
申请日：2024-05-24
Applicant: Nvidia Corporation
Inventor： Aayush Prakash , Shoubhik Debnath , Jean-Francois Lafleche , Eric Cameracci , Gavriel State , Marc Teva Law
IPC: G06V20/70 , G06F18/10 , G06F18/20 , G06F18/24 , G06V10/764 , G06V10/82 , G06V10/84 , G06V20/00 , G06V20/56
CPC classification number: G06V20/70 , G06F18/10 , G06F18/24 , G06F18/29 , G06V10/764 , G06V10/82 , G06V10/84 , G06V20/00 , G06V20/56
Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
-
公开(公告)号：US11995883B2
公开(公告)日：2024-05-28
申请号：US18163482
申请日：2023-02-02
Applicant: Nvidia Corporation
Inventor： Aayush Prakash , Shoubhik Debnath , Jean-Francois Lafleche , Eric Cameracci , Gavriel State , Marc Teva Law
IPC: G06V10/82 , G06F18/10 , G06F18/20 , G06F18/24 , G06V10/764 , G06V10/84 , G06V20/00 , G06V20/56 , G06V20/70
CPC classification number: G06V10/82 , G06F18/10 , G06F18/24 , G06F18/29 , G06V10/764 , G06V10/84 , G06V20/00 , G06V20/70 , G06V20/56
Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
-
公开(公告)号：US20230177826A1
公开(公告)日：2023-06-08
申请号：US18163482
申请日：2023-02-02
Applicant: Nvidia Corporation
Inventor： Aayush Prakash , Shoubhik Debnath , Jean-Francois Lafleche , Eric Cameracci , Gavriel State , Marc Teva Law
CPC classification number: G06V10/82 , G06V20/70 , G06F18/10 , G06F18/24 , G06F18/29 , G06V10/764 , G06V10/84 , G06V20/00 , G06V20/56
Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.011 seconds)
