-
公开(公告)号：US11847538B2
公开(公告)日：2023-12-19
申请号：US17317698
申请日：2021-05-11
申请人： NVIDIA Corporation
发明人： Tianshi Cao , Alex Bie , Karsten Julian Kreis , Sanja Fidler , Arash Vahdat
IPC分类号： G06N20/00 , G06F18/214 , G06F21/62 , G06N3/08 , G06V20/56
CPC分类号： G06N20/00 , G06F18/214 , G06F21/6218 , G06N3/08 , G06V20/56
摘要： Apparatuses, systems, and techniques to train a generative model based at least in part on a private dataset. In at least one embodiment, the generative model is trained based at least in part on a differentially private Sinkhorn algorithm, for example, using backpropagation with gradient descent to determine a gradient of a set of parameters of the generative models and modifying the set of parameters based at least in part on the gradient.
-
公开(公告)号：US20240212261A1
公开(公告)日：2024-06-27
申请号：US18412228
申请日：2024-01-12
申请人： Nvidia Corporation
发明人： Towaki Alan Takikawa , Joey Litalien , Kangxue Yin , Karsten Julian Kreis , Charles Loop , Morgan McGuire , Sanja Fidler
CPC分类号： G06T15/08 , G06T15/005 , G06T17/005 , G06T2210/36
摘要： Systems and methods are described for rendering complex surfaces or geometry. In at least one embodiment, neural signed distance functions (SDFs) can be used that efficiently capture multiple levels of detail (LODs), and that can be used to reconstruct multi-dimensional geometry or surfaces with high image quality. An example architecture can represent complex shapes in a compressed format with high visual fidelity, and can generalize across different geometries from a single learned example. Extremely small multi-layer perceptrons (MHLPs) can be used with an octree-based feature representation for the learned neural SDFs.
-
公开(公告)号：US20220172423A1
公开(公告)日：2022-06-02
申请号：US17314182
申请日：2021-05-07
申请人： Nvidia Corporation
发明人： Towaki Alan Takikawa , Joey Litalien , Kangxue Yin , Karsten Julian Kreis , Charles Loop , Morgan McGuire , Sanja Fidler
摘要： Systems and methods are described for rendering complex surfaces or geometry. In at least one embodiment, neural signed distance functions (SDFs) can be used that efficiently capture multiple levels of detail (LODs), and that can be used to reconstruct multi-dimensional geometry or surfaces with high image quality. An example architecture can represent complex shapes in a compressed format with high visual fidelity, and can generalize across different geometries from a single learned example. Extremely small multi-layer perceptrons (MLPs) can be used with an octree-based feature representation for the learned neural SDFs.
-
公开(公告)号：US20240171788A1
公开(公告)日：2024-05-23
申请号：US18181729
申请日：2023-03-10
申请人： NVIDIA Corporation
发明人： Karsten Julian Kreis , Robin Rombach , Andreas Blattmann , Seung Wook Kim , Huan Ling , Sanja Fidler , Tim Dockhorn
CPC分类号： H04N21/234363 , G06T9/00 , G06V10/24 , G06V10/25 , G06V10/82 , H04N7/0117
摘要： In various examples, systems and methods are disclosed relating to aligning images into frames of a first video using at least one first temporal attention layer of a neural network model. The first video has a first spatial resolution. A second video having a second spatial resolution is generated by up-sampling the first video using at least one second temporal attention layer of an up-sampler neural network model, wherein the second spatial resolution is higher than the first spatial resolution.
-
公开(公告)号：US11875449B2
公开(公告)日：2024-01-16
申请号：US17745478
申请日：2022-05-16
申请人： Nvidia Corporation
发明人： Towaki Alan Takikawa , Joey Litalien , Kangxue Yin , Karsten Julian Kreis , Charles Loop , Morgan McGuire , Sanja Fidler
CPC分类号： G06T15/08 , G06T17/005 , G06T2210/36
摘要： Systems and methods are described for rendering complex surfaces or geometry. In at least one embodiment, neural signed distance functions (SDFs) can be used that efficiently capture multiple levels of detail (LODs), and that can be used to reconstruct multi-dimensional geometry or surfaces with high image quality. An example architecture can represent complex shapes in a compressed format with high visual fidelity, and can generalize across different geometries from a single learned example. Extremely small multi-layer perceptrons (MLPs) can be used with an octree-based feature representation for the learned neural SDFs.
-
公开(公告)号：US11335056B1
公开(公告)日：2022-05-17
申请号：US17314182
申请日：2021-05-07
申请人： Nvidia Corporation
发明人： Towaki Alan Takikawa , Joey Litalien , Kangxue Yin , Karsten Julian Kreis , Charles Loop , Morgan McGuire , Sanja Fidler
摘要： Systems and methods are described for rendering complex surfaces or geometry. In at least one embodiment, neural signed distance functions (SDFs) can be used that efficiently capture multiple levels of detail (LODs), and that can be used to reconstruct multi-dimensional geometry or surfaces with high image quality. An example architecture can represent complex shapes in a compressed format with high visual fidelity, and can generalize across different geometries from a single learned example. Extremely small multi-layer perceptrons (MLPs) can be used with an octree-based feature representation for the learned neural SDFs.
-
公开(公告)号：US20240256831A1
公开(公告)日：2024-08-01
申请号：US18159815
申请日：2023-01-26
申请人： NVIDIA Corporation
发明人： Daiqing Li , Huan Ling , Seung Wook Kim , Karsten Julian Kreis , Antonio Torralba Barriuso , Sanja Fidler , Amlan Kar
IPC分类号： G06N3/045 , G06T5/00 , G06V10/774 , G06V10/82
CPC分类号： G06N3/045 , G06T5/70 , G06V10/7753 , G06V10/82
摘要： In various examples, systems and methods are disclosed relating to generating a response from image and/or video input for image/video-based artificial intelligence (AI) systems and applications. Systems and methods are disclosed for a first model (e.g., a teacher model) distilling its knowledge to a second model (a student model). The second model receives a downstream image in a downstream task and generates at least one feature. The first model generates first features corresponding to an image which can be a real image or a synthetic image. The second model generates second features using the image as an input to the second model. Loss with respect to first features is determined. The second model is updated using the loss.
-
8.发明公开公开(公告)号：US20240160888A1
公开(公告)日：2024-05-16
申请号：US18193982
申请日：2023-03-31
申请人： NVIDIA Corporation
IPC分类号： G06N3/02
CPC分类号： G06N3/02
摘要： In various examples, systems and methods are disclosed relating to neural networks for realistic and controllable agent simulation using guided trajectories. The neural networks can be configured using training data including trajectories and other state data associated with subjects or agents and remote or neighboring subjects or agents, as well as context data representative of an environment in which the subjects are present. The trajectories can be determining using the neural networks and using various forms of guidance for controllability, such as for waypoint navigation, obstacle avoidance, and group movement.
-
公开(公告)号：US20220067983A1
公开(公告)日：2022-03-03
申请号：US17006702
申请日：2020-08-28
申请人： NVIDIA Corporation
摘要： Apparatuses, systems, and techniques to generate complete depictions of objects based on a partial depiction of the object. In at least one embodiment, an image of a complete object is generated by one or more neural networks, based on an image of a portion of the object, using an encoder of the one or more neural networks trained using training data generated from output of a decoder of the one or more neural networks.
-
公开(公告)号：US20240096064A1
公开(公告)日：2024-03-21
申请号：US17832400
申请日：2022-06-03
申请人： NVIDIA Corporation
发明人： Daiqing Li , Huan Ling , Seung Wook Kim , Karsten Julian Kreis , Sanja Fidler , Antonio Torralba Barriuso
IPC分类号： G06V10/774 , G06V10/764 , G06V10/82
CPC分类号： G06V10/774 , G06V10/764 , G06V10/82
摘要： Apparatuses, systems, and techniques to annotate images using neural models. In at least one embodiment, neural networks generate mask information from labels of one or more objects within one or more images identified by one or more other neural networks.
-
-
-
-
-
-
-
-
-
搜索结果
14 条记录 (耗时 0.015 秒)
