知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

69 条记录 (耗时 0.019 秒)

    Style-based architecture for generative neural networks
    1.
    发明授权
    Style-based architecture for generative neural networks 有权

    公开(公告)号：US11455790B2

    公开(公告)日：2022-09-27

    申请号：US16418317

    申请日：2019-05-21

    申请人： NVIDIA Corporation

    发明人： Tero Tapani Karras ,  Timo Oskari Aila ,  Samuli Matias Laine

    IPC分类号： G06N3/08 ,  G06V10/82 ,  G06N3/04

    摘要： A style-based generative network architecture enables scale-specific control of synthesized output data, such as images. During training, the style-based generative neural network (generator neural network) includes a mapping network and a synthesis network. During prediction, the mapping network may be omitted, replicated, or evaluated several times. The synthesis network may be used to generate highly varied, high-quality output data with a wide variety of attributes. For example, when used to generate images of people's faces, the attributes that may vary are age, ethnicity, camera viewpoint, pose, face shape, eyeglasses, colors (eyes, hair, etc.), hair style, lighting, background, etc. Depending on the task, generated output data may include images, audio, video, three-dimensional (3D) objects, text, etc.

    TRAINING NEURAL NETWORKS WITH LIMITED DATA USING INVERTIBLE AUGMENTATION OPERATORS
    3.
    发明申请
    TRAINING NEURAL NETWORKS WITH LIMITED DATA USING INVERTIBLE AUGMENTATION OPERATORS 有权

    公开(公告)号：US20210383241A1

    公开(公告)日：2021-12-09

    申请号：US17210934

    申请日：2021-03-24

    申请人： NVIDIA Corporation

    发明人： Tero Tapani Karras ,  Miika Samuli Aittala ,  Janne Johannes Hellsten ,  Samuli Matias Laine ,  Jaakko T. Lehtinen ,  Timo Oskari Aila

    IPC分类号： G06N3/08 ,  G06N3/04

    摘要： Embodiments of the present disclosure relate to a technique for training neural networks, such as a generative adversarial neural network (GAN), using a limited amount of data. Training GANs using too little example data typically leads to discriminator overfitting, causing training to diverge and produce poor results. An adaptive discriminator augmentation mechanism is used that significantly stabilizes training with limited data providing the ability to train high-quality GANs. An augmentation operator is applied to the distribution of inputs to a discriminator used to train a generator, representing a transformation that is invertible to ensure there is no leakage of the augmentations into the images generated by the generator. Reducing the amount of training data that is needed to achieve convergence has the potential to considerably help many applications and may the increase use of generative models in fields such as medicine.

    BEAM TRACING
    5.
    发明申请
    BEAM TRACING 审中-公开

    公开(公告)号：US20180182158A1

    公开(公告)日：2018-06-28

    申请号：US15393057

    申请日：2016-12-28

    申请人： NVIDIA Corporation

    发明人： Tero Tapani Karras ,  Timo Oskari Aila ,  Samuli Matias Laine ,  John Erik Lindholm

    IPC分类号： G06T15/06 ,  G06T1/20

    CPC分类号： G06T15/06 ,  G06T2210/12

    摘要： An apparatus, computer readable medium, and method are disclosed for performing an intersection query between a query beam and a target bounding volume. The target bounding volume may comprise an axis-aligned bounding box (AABB) associated with a bounding volume hierarchy (BVH) tree. An intersection query comprising beam information associated with the query beam and slab boundary information for a first dimension of a target bounding volume is received. Intersection parameter values are calculated for the first dimension based on the beam information and the slab boundary information and a slab intersection case is determined for the first dimension based on the beam information. A parametric variable range for the first dimension is assigned based on the slab intersection case and the intersection parameter values and it is determined whether the query beam intersects the target bounding volume based on at least the parametric variable range for the first dimension.

    Relative encoding for a block-based bounding volume hierarchy
    7.
    发明授权
    Relative encoding for a block-based bounding volume hierarchy 有权
    基于块的边界卷分层的相对编码

    公开(公告)号：US09552664B2

    公开(公告)日：2017-01-24

    申请号：US14589910

    申请日：2015-01-05

    申请人： NVIDIA Corporation

    发明人： Samuli Matias Laine ,  Timo Oskari Aila ,  Tero Tapani Karras

    IPC分类号： G06T15/10 ,  G06T17/00 ,  G06T15/06

    CPC分类号： G06T9/40 ,  G06T9/001 ,  G06T15/005 ,  G06T15/04 ,  G06T15/06 ,  G06T15/08 ,  G06T15/10 ,  G06T15/80 ,  G06T17/005 ,  G06T17/10

    摘要： A system, method, and computer program product for implementing a tree traversal operation for a tree data structure is disclosed. The method includes the steps of receiving at least a portion of a tree data structure that represents a tree having a plurality of nodes and processing, via a tree traversal operation algorithm executed by a processor, one or more nodes of the tree data structure by intersecting the one or more nodes of the tree data structure with a query data structure. A first node of the tree data structure is associated with a first local coordinate system and a second node of the tree data structure is associated with a second local coordinate system, the first node being an ancestor of the second node, and the first local coordinate system and the second local coordinate system are both specified relative to a global coordinate system.

    摘要翻译： 公开了一种用于实现树数据结构的树遍历操作的系统，方法和计算机程序产品。 该方法包括以下步骤：接收表示具有多个节点的树的树数据结构的至少一部分，并且经由处理器执行的树遍历运算算法，通过相交来处理树数据结构的一个或多个节点 具有查询数据结构的树数据结构的一个或多个节点。 树数据结构的第一节点与第一局部坐标系相关联，并且树数据结构的第二节点与第二局部坐标系相关联，第一节点是第二节点的祖先，第一局部坐标 系统和第二局部坐标系均相对于全局坐标系来指定。

    BEAM TRACING
    8.
    发明申请
    BEAM TRACING 有权
    光束追踪

    公开(公告)号：US20160071310A1

    公开(公告)日：2016-03-10

    申请号：US14662090

    申请日：2015-03-18

    申请人： NVIDIA Corporation

    发明人： Tero Tapani Karras ,  Timo Oskari Aila ,  Samuli Matias Laine ,  John Erik Lindholm

    IPC分类号： G06T15/06 ,  G06T15/80 ,  G06T15/00

    CPC分类号： G06F17/30961 ,  G06F17/30327 ,  G06F17/30563 ,  G06T1/60 ,  G06T9/40 ,  G06T15/005 ,  G06T15/06 ,  G06T15/08 ,  G06T15/10 ,  G06T15/80 ,  G06T17/10 ,  H04N19/174 ,  H04N19/44

    摘要： An apparatus, computer readable medium, and method are disclosed for performing an intersection query between a query beam and a target bounding volume. The target bounding volume may comprise an axis-aligned bounding box (AABB) associated with a bounding volume hierarchy (BVH) tree. An intersection query comprising beam information associated with the query beam and slab boundary information for a first dimension of a target bounding volume is received. Intersection parameter values are calculated for the first dimension based on the beam information and the slab boundary information and a slab intersection case is determined for the first dimension based on the beam information. A parametric variable range for the first dimension is assigned based on the slab intersection case and the intersection parameter values and it is determined whether the query beam intersects the target bounding volume based on at least the parametric variable range for the first dimension.

    摘要翻译： 公开了一种用于执行查询光束和目标界限卷之间的交叉查询的装置，计算机可读介质和方法。 目标边界体积可以包括与边界体积分层（BVH）树相关联的轴对齐边界框（AABB）。 接收包括与查询波束相关联的波束信息和用于目标边界体积的第一维度的平板边界信息的交叉点查询。 基于波束信息和平板边界信息，针对第一维度计算交点参数值，并且基于波束信息为第一维度确定板交集情况。 基于板交集案例和交集参数值分配第一维度的参数变量范围，并且基于至少第一维度的参数可变范围确定查询梁是否与目标界限卷相交。

    System, method, and computer program product implementing an algorithm for performing thin voxelization of a three-dimensional model
    9.
    发明授权
    System, method, and computer program product implementing an algorithm for performing thin voxelization of a three-dimensional model 有权
    实现用于执行三维模型的薄体素化的算法的系统，方法和计算机程序产品

    公开(公告)号：US09245363B2

    公开(公告)日：2016-01-26

    申请号：US13725015

    申请日：2012-12-21

    申请人： NVIDIA Corporation

    发明人： Samuli Matias Laine

    IPC分类号： G06T11/40 ,  G06T17/00 ,  G06T15/08

    CPC分类号： G06T11/40 ,  G06T15/08 ,  G06T17/00

    摘要： A system, method, and computer program product for implementing an algorithm for performing thin voxelization is disclosed. The thin voxelization algorithm receives a surface, maps the surface onto a plurality of volumetric picture elements (voxels), and generates a value for each voxel in the plurality of voxels that intersects with the surface. A voxel intersects with the surface when the surface intersects a crosshair shape associated with the voxel.

    摘要翻译： 公开了一种用于实现用于执行薄体素化的算法的系统，方法和计算机程序产品。 薄体素化算法接收表面，将表面映射到多个体积像素（体素）上，并且生成与表面相交的多个体素中的每个体素的值。 当表面与与体素相关联的十字线形状相交时，体素与表面相交。