中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

172 records (took 0.024 seconds)

    CREATING AN IMAGE UTILIZING A MAP REPRESENTING DIFFERENT CLASSES OF PIXELS
    151.
    发明申请
    CREATING AN IMAGE UTILIZING A MAP REPRESENTING DIFFERENT CLASSES OF PIXELS 有权

    公开(公告)号：US20220012536A1

    公开(公告)日：2022-01-13

    申请号：US17483688

    申请日：2021-09-23

    Applicant: NVIDIA Corporation

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

    IPC: G06K9/62 ,  G06K9/72 ,  G06K9/68 ,  G06K9/46

    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.

    TRANSFORMING CONVOLUTIONAL NEURAL NETWORKS FOR VISUAL SEQUENCE LEARNING
    153.
    发明申请
    TRANSFORMING CONVOLUTIONAL NEURAL NETWORKS FOR VISUAL SEQUENCE LEARNING 有权

    公开(公告)号：US20210271977A1

    公开(公告)日：2021-09-02

    申请号：US17325024

    申请日：2021-05-19

    Applicant: NVIDIA Corporation

    Inventor： Xiaodong Yang ,  Pavlo Molchanov ,  Jan Kautz

    IPC: G06N3/08 ,  G06K9/00 ,  G06N3/04 ,  G06K9/62

    Abstract: A method, computer readable medium, and system are disclosed for visual sequence learning using neural networks. The method includes the steps of replacing a non-recurrent layer within a trained convolutional neural network model with a recurrent layer to produce a visual sequence learning neural network model and transforming feedforward weights for the non-recurrent layer into input-to-hidden weights of the recurrent layer to produce a transformed recurrent layer. The method also includes the steps of setting hidden-to-hidden weights of the recurrent layer to initial values and processing video image data by the visual sequence learning neural network model to generate classification or regression output data.

    3D plane detection and reconstruction using a monocular image
    155.
    发明授权
    3D plane detection and reconstruction using a monocular image 有权

    公开(公告)号：US11037051B2

    公开(公告)日：2021-06-15

    申请号：US16565885

    申请日：2019-09-10

    Applicant: NVIDIA Corporation

    Inventor： Kihwan Kim ,  Jinwei Gu ,  Chen Liu ,  Jan Kautz

    IPC: G06N3/04 ,  G06T7/11 ,  G06T7/50 ,  G06K9/62

    Abstract: Planar regions in three-dimensional scenes offer important geometric cues in a variety of three-dimensional perception tasks such as scene understanding, scene reconstruction, and robot navigation. Image analysis to detect planar regions can be performed by a deep learning architecture that includes a number of neural networks configured to estimate parameters for the planar regions. The neural networks process an image to detect an arbitrary number of plane objects in the image. Each plane object is associated with a number of estimated parameters including bounding box parameters, plane normal parameters, and a segmentation mask. Global parameters for the image, including a depth map, can also be estimated by one of the neural networks. Then, a segmentation refinement network jointly optimizes (i.e., refines) the segmentation masks for each instance of the plane objects and combines the refined segmentation masks to generate an aggregate segmentation mask for the image.

    Domain stylization using a neural network model
    158.
    发明授权
    Domain stylization using a neural network model 有权

    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.

    CROSS-DOMAIN IMAGE PROCESSING FOR OBJECT RE-IDENTIFICATION
    160.
    发明申请
    CROSS-DOMAIN IMAGE PROCESSING FOR OBJECT RE-IDENTIFICATION 有权

    公开(公告)号：US20210064907A1

    公开(公告)日：2021-03-04

    申请号：US16998890

    申请日：2020-08-20

    Applicant: NVIDIA Corporation

    Inventor： Xiaodong Yang ,  Yang Zou ,  Zhiding Yu ,  Jan Kautz

    IPC: G06K9/44 ,  G06K9/46 ,  G06K9/62

    Abstract: Object re-identification refers to a process by which images that contain an object of interest are retrieved from a set of images captured using disparate cameras or in disparate environments. Object re-identification has many useful applications, particularly as it is applied to people (e.g. person tracking). Current re-identification processes rely on convolutional neural networks (CNNs) that learn re-identification for a particular object class from labeled training data specific to a certain domain (e.g. environment), but that do not apply well in other domains. The present disclosure provides cross-domain disentanglement of id-related and id-unrelated factors. In particular, the disentanglement is performed using a labeled image set and an unlabeled image set, respectively captured from different domains but for a same object class. The identification-related features may then be used to train a neural network to perform re-identification of objects in that object class from images captured from the second domain.

Patent Agency Ranking