中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

12 records (took 0.011 seconds)

    IMAGE GENERATION USING ONE OR MORE NEURAL NETWORKS
    1.
    发明申请
    IMAGE GENERATION USING ONE OR MORE NEURAL NETWORKS 审中-公开

    公开(公告)号：WO2021067126A1

    公开(公告)日：2021-04-08

    申请号：PCT/US2020/052665

    申请日：2020-09-25

    Applicant: NVIDIA CORPORATION

    Inventor： LIU, Ming-Yu

    IPC: G06T11/00

    Abstract: Apparatuses, systems, and techniques are presented to generate or manipulate digital images. In at least one embodiment, a network is trained to generate modified images including user-selected features.

    LEARNING TO GENERATE SYNTHETIC DATASETS FOR TRAINING NEURAL NETWORKS
    7.
    发明申请
    LEARNING TO GENERATE SYNTHETIC DATASETS FOR TRAINING NEURAL NETWORKS 审中-公开

    公开(公告)号：WO2020102733A1

    公开(公告)日：2020-05-22

    申请号：PCT/US2019/061820

    申请日：2019-11-15

    Applicant: NVIDIA CORPORATION

    Inventor： KAR, Amlan ,  PRAKASH, Aayush ,  LIU, Ming-Yu ,  ACUNA MARRERO, David Jesus ,  BARRIUSO, Antonio Torralba ,  FIDLER, Sanja

    IPC: G06N3/04 ,  G06N3/08 ,  G06N20/20 ,  G06T7/00

    Abstract: In various examples, a generative model is used to synthesize datasets for use in training a downstream machine learning model to perform an associated task. The synthesized datasets may be generated by sampling a scene graph from a scene grammar – such as a probabilistic grammar – and applying the scene graph to the generative model to compute updated scene graphs more representative of object attribute distributions of real-world datasets. The downstream machine learning model may be validated against a real-world validation dataset, and the performance of the model on the real-world validation dataset may be used as an additional factor in further training or fine-tuning the generative model for generating the synthesized datasets specific to the task of the downstream machine learning model.

    SYNTHESIZING HIGH RESOLUTION 3D SHAPES FROM LOWER RESOLUTION REPRESENTATIONS FOR SYNTHETIC DATA GENERATION SYSTEMS AND APPLICATIONS
    8.
    发明申请
    SYNTHESIZING HIGH RESOLUTION 3D SHAPES FROM LOWER RESOLUTION REPRESENTATIONS FOR SYNTHETIC DATA GENERATION SYSTEMS AND APPLICATIONS 审中-公开

    公开(公告)号：WO2022250796A1

    公开(公告)日：2022-12-01

    申请号：PCT/US2022/024306

    申请日：2022-04-11

    Applicant: NVIDIA CORPORATION

    Inventor： SHEN, Tianchang ,  GAO, Jun ,  YIN, Kangxue ,  LIU, Ming-Yu ,  FIDLER, Sanja

    IPC: G06T17/20

    Abstract: In various examples, a deep three-dimensional (3D) conditional generative model is implemented that can synthesize high resolution 3D shapes using simple guides – such as coarse voxels, point clouds, etc. – by marrying implicit and explicit 3D representations into a hybrid 3D representation. The present approach may directly optimize for the reconstructed surface, allowing for the synthesis of finer geometric details with fewer artifacts. The systems and methods described herein may use a deformable tetrahedral grid that encodes a discretized signed distance function (SDF) and a differentiable marching tetrahedral layer that converts the implicit SDF representation to an explicit surface mesh representation. This combination allows joint optimization of the surface geometry and topology as well as generation of the hierarchy of subdivisions using reconstruction and adversarial losses defined explicitly on the surface mesh.

    ITERATIVE SPATIAL GRAPH GENERATION
    10.
    发明申请
    ITERATIVE SPATIAL GRAPH GENERATION 审中-公开

    公开(公告)号：WO2020198084A1

    公开(公告)日：2020-10-01

    申请号：PCT/US2020/024083

    申请日：2020-03-21

    Applicant: NVIDIA CORPORATION

    Inventor： LI, Daiqing ,  FIDLER, Sanja ,  CHU, Hang ,  ACUNA MARRERO, David Jesus ,  KAR, Amlan ,  SHUGRINA, Maria ,  LIU, Ming-Yu ,  TORRALBA, Antonio

    IPC: G06F30/27 ,  G06F30/13 ,  G06F16/901 ,  G06T3/00

    Abstract: A generative model can be used for generation of spatial layouts and graphs. Such a model can progressively grow these layouts and graphs based on local statistics, where nodes can represent spatial control points of the layout, and edges can represent segments or paths between nodes, such as may correspond to road segments. A generative model can utilize an encoder-decoder architecture where the encoder is a recurrent neural network (RNN) that encodes local incoming paths into a node and the decoder is another RNN that generates outgoing nodes and edges connecting an existing node to the newly generated nodes. Generation is done iteratively, and can finish once all nodes are visited or another end condition is satisfied. Such a model can generate layouts by additionally conditioning on a set of attributes, giving control to a user in generating the layout.

Patent Agency Ranking