知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

172 records (took 0.024 seconds)

    FUTURE OBJECT TRAJECTORY PREDICTIONS FOR AUTONOMOUS MACHINE APPLICATIONS
    61.
    发明申请
    FUTURE OBJECT TRAJECTORY PREDICTIONS FOR AUTONOMOUS MACHINE APPLICATIONS 审中-公开

    公开(公告)号：US20200082248A1

    公开(公告)日：2020-03-12

    申请号：US16564978

    申请日：2019-09-09

    Applicant: NVIDIA Corporation

    Inventor： Ruben Villegas ,  Alejandro Troccoli ,  Iuri Frosio ,  Stephen Tyree ,  Wonmin Byeon ,  Jan Kautz

    IPC: G06N3/04 ,  G06N3/08 ,  G05D1/02

    Abstract: In various examples, historical trajectory information of objects in an environment may be tracked by an ego-vehicle and encoded into a state feature. The encoded state features for each of the objects observed by the ego-vehicle may be used—e.g., by a bi-directional long short-term memory (LSTM) network—to encode a spatial feature. The encoded spatial feature and the encoded state feature for an object may be used to predict lateral and/or longitudinal maneuvers for the object, and the combination of this information may be used to determine future locations of the object. The future locations may be used by the ego-vehicle to determine a path through the environment, or may be used by a simulation system to control virtual objects—according to trajectories determined from the future locations—through a simulation environment.

    FAST MULTI-SCALE POINT CLOUD REGISTRATION WITH A HIERARCHICAL GAUSSIAN MIXTURE
    62.
    发明申请
    FAST MULTI-SCALE POINT CLOUD REGISTRATION WITH A HIERARCHICAL GAUSSIAN MIXTURE 审中-公开

    公开(公告)号：US20190319851A1

    公开(公告)日：2019-10-17

    申请号：US16351312

    申请日：2019-03-12

    Applicant: NVIDIA Corporation

    Inventor： Benjamin David Eckart ,  Kihwan Kim ,  Jan Kautz

    IPC: H04L12/24 ,  H04L29/08 ,  G06F16/22

    Abstract: Point cloud registration sits at the core of many important and challenging 3D perception problems including autonomous navigation, object/scene recognition, and augmented reality (AR). A new registration algorithm is presented that achieves speed and accuracy by registering a point cloud to a representation of a reference point cloud. A target point cloud is registered to the reference point cloud by iterating through a number of cycles of an EM algorithm where, during an Expectation step, each point in the target point cloud is associated with a node of a hierarchical tree data structure and, during a Maximization step, an estimated transformation is determined based on the association of the points with corresponding nodes of the hierarchical tree data structure. The estimated transformation is determined by solving a minimization problem associated with a sum, over a number of mixture components, over terms related to a Mahalanobis distance.

    System and method for optical flow estimation
    63.
    发明授权
    System and method for optical flow estimation 有权

    公开(公告)号：US10424069B2

    公开(公告)日：2019-09-24

    申请号：US15942213

    申请日：2018-03-30

    Applicant: NVIDIA Corporation

    Inventor： Deqing Sun ,  Xiaodong Yang ,  Ming-Yu Liu ,  Jan Kautz

    IPC: G06T7/207 ,  G06N5/04 ,  G06T3/00 ,  G06T7/00 ,  G06T7/246 ,  G06N3/04 ,  G06N3/08

    Abstract: A method, computer readable medium, and system are disclosed for estimating optical flow between two images. A first pyramidal set of features is generated for a first image and a partial cost volume for a level of the first pyramidal set of features is computed, by a neural network, using features at the level of the first pyramidal set of features and warped features extracted from a second image, where the partial cost volume is computed across a limited range of pixels that is less than a full resolution of the first image, in pixels, at the level. The neural network processes the features and the partial cost volume to produce a refined optical flow estimate for the first image and the second image.

    Domain Stylization Using a Neural Network Model
    64.
    发明申请
    Domain Stylization Using a Neural Network Model 审中-公开

    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.

    CREATING AN IMAGE UTILIZING A MAP REPRESENTING DIFFERENT CLASSES OF PIXELS
    67.
    发明申请
    CREATING AN IMAGE UTILIZING A MAP REPRESENTING DIFFERENT CLASSES OF PIXELS 审中-公开

    公开(公告)号：US20190147296A1

    公开(公告)日：2019-05-16

    申请号：US16188920

    申请日：2018-11-13

    Applicant: NVIDIA Corporation

    Inventor： Ting-Chun Wang ,  Ming-Yu Liu ,  Bryan Christopher Catanzaro ,  Jan Kautz ,  Andrew J. Tao

    IPC: G06K9/62 ,  G06K9/68 ,  G06K9/72

    Abstract: A method, computer readable medium, and system are disclosed for creating an image utilizing a map representing different classes of specific pixels within a scene. One or more computing systems use the map to create a preliminary image. This preliminary image is then compared to an original image that was used to create the map. A determination is made whether the preliminary image matches the original image, and results of the determination are used to adjust the computing systems that created the preliminary image, which improves a performance of such computing systems. The adjusted computing systems are then used to create images based on different input maps representing various object classes of specific pixels within a scene.

    Learning-Based Camera Pose Estimation From Images of an Environment
    68.
    发明申请
    Learning-Based Camera Pose Estimation From Images of an Environment 审中-公开

    公开(公告)号：US20190108651A1

    公开(公告)日：2019-04-11

    申请号：US16137064

    申请日：2018-09-20

    Applicant: NVIDIA Corporation

    Inventor： Jinwei Gu ,  Samarth Manoj Brahmbhatt ,  Kihwan Kim ,  Jan Kautz

    IPC: G06T7/80 ,  G06T7/00

    Abstract: A deep neural network (DNN) system learns a map representation for estimating a camera position and orientation (pose). The DNN is trained to learn a map representation corresponding to the environment, defining positions and attributes of structures, trees, walls, vehicles, walls, etc. The DNN system learns a map representation that is versatile and performs well for many different environments (indoor, outdoor, natural, synthetic, etc.). The DNN system receives images of an environment captured by a camera (observations) and outputs an estimated camera pose within the environment. The estimated camera pose is used to perform camera localization, i.e., recover the three-dimensional (3D) position and orientation of a moving camera, which is a fundamental task in computer vision with a wide variety of applications in robot navigation, car localization for autonomous driving, device localization for mobile navigation, and augmented/virtual reality.

    DUAL FORMULATION FOR A COMPUTER VISION RETENTION MODEL
    70.
    发明申请
    DUAL FORMULATION FOR A COMPUTER VISION RETENTION MODEL 有权

    公开(公告)号：US20250111661A1

    公开(公告)日：2025-04-03

    申请号：US18882629

    申请日：2024-09-11

    Applicant: NVIDIA Corporation

    Inventor： Ali Hatamizadeh ,  Michael Ranzinger ,  Jan Kautz

    IPC: G06V10/82 ,  G06V10/26 ,  G06V10/774 ,  G06V10/776 ,  G06V10/94

    Abstract: Transformers are neural networks that learn context and thus meaning by tracking relationships in sequential data. The main building block of transformers is self-attention which allows for cross interaction among all input sequence tokens with each other. This scheme effectively captures short-and long-range spatial dependencies and imposes time and space quadratic complexity in terms of the input sequence length, which enables their use with Natural Language Processing (NLP) and computer vision tasks. While the training parallelism of transformers allows for competitive performance, unfortunately the inference is slow and expensive due to the computational complexity. The present disclosure provides a computer vision retention model that is configured for both parallel training and recurrent inference, which can enable competitive performance during training and fast and memory-efficient inferences during deployment.

Patent Agency Ranking