中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

14 records (took 0.013 seconds)

    FEATURE EXTRACTION WITH THREE-DIMENSIONAL INFORMATION
    1.
    发明申请
    FEATURE EXTRACTION WITH THREE-DIMENSIONAL INFORMATION 有权

    公开(公告)号：US20250131680A1

    公开(公告)日：2025-04-24

    申请号：US18802288

    申请日：2024-08-13

    Applicant: NVIDIA Corporation

    Inventor： Or Litany ,  Sanja Fidler ,  Huan Ling ,  Chenfeng Xu

    IPC: G06V10/25 ,  G06T3/18 ,  G06T7/70 ,  G06T11/00 ,  G06V20/70

    Abstract: Disclosed are systems and methods relating to extracting 3D features, such as bounding boxes. The systems can apply, to one or more features of a source image that depicts a scene using a first set of camera parameters, based on a condition view image associated with the source image, an epipolar geometric warping to determine a second set of camera parameters. The systems can generate, using a neural network, a synthetic image representing the one or more features and corresponding to the second set of camera parameters.

    NEURAL RENDERING FOR INVERSE GRAPHICS GENERATION
    4.
    发明申请
    NEURAL RENDERING FOR INVERSE GRAPHICS GENERATION 有权

    公开(公告)号：US20210279952A1

    公开(公告)日：2021-09-09

    申请号：US17193405

    申请日：2021-03-05

    Applicant: Nvidia Corporation

    Inventor： Wenzheng Chen ,  Yuxuan Zhang ,  Sanja Fidler ,  Huan Ling ,  Jun Gao ,  Antonio Torralba Barriuso

    IPC: G06T17/00 ,  G06T15/10 ,  G06N3/04 ,  G06N3/08

    Abstract: Approaches are presented for training an inverse graphics network. An image synthesis network can generate training data for an inverse graphics network. In turn, the inverse graphics network can teach the synthesis network about the physical three-dimensional (3D) controls. Such an approach can provide for accurate 3D reconstruction of objects from 2D images using the trained inverse graphics network, while requiring little annotation of the provided training data. Such an approach can extract and disentangle 3D knowledge learned by generative models by utilizing differentiable renderers, enabling a disentangled generative model to function as a controllable 3D “neural renderer,” complementing traditional graphics renderers.

    NEURAL RENDERING FOR INVERSE GRAPHICS GENERATION
    7.
    发明申请
    NEURAL RENDERING FOR INVERSE GRAPHICS GENERATION 有权

    公开(公告)号：US20230134690A1

    公开(公告)日：2023-05-04

    申请号：US17981770

    申请日：2022-11-07

    Applicant: Nvidia Corporation

    Inventor： Wenzheng Chen ,  Yuxuan Zhang ,  Sanja Fidler ,  Huan Ling ,  Jun Gao ,  Antonio Torralba Barriuso

    IPC: G06T17/00 ,  G06N3/088 ,  G06T15/10 ,  G06N3/045

    Abstract: Approaches are presented for training an inverse graphics network. An image synthesis network can generate training data for an inverse graphics network. In turn, the inverse graphics network can teach the synthesis network about the physical three-dimensional (3D) controls. Such an approach can provide for accurate 3D reconstruction of objects from 2D images using the trained inverse graphics network, while requiring little annotation of the provided training data. Such an approach can extract and disentangle 3D knowledge learned by generative models by utilizing differentiable renderers, enabling a disentangled generative model to function as a controllable 3D “neural renderer,” complementing traditional graphics renderers.

    HIGH-PRECISION SEMANTIC IMAGE EDITING USING NEURAL NETWORKS FOR SYNTHETIC DATA GENERATION SYSTEMS AND APPLICATIONS
    9.
    发明申请
    HIGH-PRECISION SEMANTIC IMAGE EDITING USING NEURAL NETWORKS FOR SYNTHETIC DATA GENERATION SYSTEMS AND APPLICATIONS 有权

    公开(公告)号：US20220383570A1

    公开(公告)日：2022-12-01

    申请号：US17827394

    申请日：2022-05-27

    Applicant: NVIDIA Corporation

    Inventor： Huan Ling ,  Karsten Kreis ,  Daiqing Li ,  Seung Wook Kim ,  Antonio Torralba Barriuso ,  Sanja Fidler

    IPC: G06T11/60 ,  G06T7/10 ,  G06V10/776 ,  G06V10/774

    Abstract: In various examples, high-precision semantic image editing for machine learning systems and applications are described. For example, a generative adversarial network (GAN) may be used to jointly model images and their semantic segmentations based on a same underlying latent code. Image editing may be achieved by using segmentation mask modifications (e.g., provided by a user, or otherwise) to optimize the latent code to be consistent with the updated segmentation, thus effectively changing the original, e.g., RGB image. To improve efficiency of the system, and to not require optimizations for each edit on each image, editing vectors may be learned in latent space that realize the edits, and that can be directly applied on other images with or without additional optimizations. As a result, a GAN in combination with the optimization approaches described herein may simultaneously allow for high precision editing in real-time with straightforward compositionality of multiple edits.

Patent Agency Ranking