知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

82 records (took 0.017 seconds)

    GUIDED HALLUCINATION FOR MISSING IMAGE CONTENT USING A NEURAL NETWORK
    11.
    发明申请
    GUIDED HALLUCINATION FOR MISSING IMAGE CONTENT USING A NEURAL NETWORK 审中-公开

    公开(公告)号：US20190355103A1

    公开(公告)日：2019-11-21

    申请号：US16353195

    申请日：2019-03-14

    Applicant: NVIDIA Corporation

    Inventor： Seung-Hwan Baek ,  Kihwan Kim ,  Jinwei Gu ,  Orazio Gallo ,  Alejandro Jose Troccoli ,  Ming-Yu Liu ,  Jan Kautz

    IPC: G06T5/00 ,  G06K9/72 ,  G06T5/50 ,  G06T3/40 ,  G06K9/62

    Abstract: Missing image content is generated using a neural network. In an embodiment, a high resolution image and associated high resolution semantic label map are generated from a low resolution image and associated low resolution semantic label map. The input image/map pair (low resolution image and associated low resolution semantic label map) lacks detail and is therefore missing content. Rather than simply enhancing the input image/map pair, data missing in the input image/map pair is improvised or hallucinated by a neural network, creating plausible content while maintaining spatio-temporal consistency. Missing content is hallucinated to generate a detailed zoomed in portion of an image. Missing content is hallucinated to generate different variations of an image, such as different seasons or weather conditions for a driving video.

    MULTI-MODAL IMAGE TRANSLATION USING NEURAL NETWORKS
    12.
    发明申请
    MULTI-MODAL IMAGE TRANSLATION USING NEURAL NETWORKS 审中-公开

    公开(公告)号：US20190279075A1

    公开(公告)日：2019-09-12

    申请号：US16279671

    申请日：2019-02-19

    Applicant: Nvidia Corporation

    Inventor： Ming-Yu Liu ,  Xun Huang

    IPC: G06N3/04 ,  G06N5/04 ,  G06F17/18 ,  G06T3/00

    Abstract: A source image is processed using an encoder network to determine a content code representative of a visual aspect of the source object represented in the source image. A target class is determined, which can correspond to an entire population of objects of a particular type. The user may specify specific objects within the target class, or a sampling can be done to select objects within the target class to use for the translation. Style codes for the selected target objects are determined that are representative of the appearance of those target objects. The target style codes are provided with the source content code as input to a translation network, which can use the codes to infer a set of images including representations of the selected target objects having the visual aspect determined from the source image.

    Photorealistic Image Stylization Using a Neural Network Model
    13.
    发明申请
    Photorealistic Image Stylization Using a Neural Network Model 审中-公开

    公开(公告)号：US20190244329A1

    公开(公告)日：2019-08-08

    申请号：US16246375

    申请日：2019-01-11

    Applicant: NVIDIA Corporation

    Inventor： Yijun Li ,  Ming-Yu Liu ,  Ming-Hsuan Yang ,  Jan Kautz

    IPC: G06T5/00 ,  G06T7/11 ,  G06N3/08

    CPC classification number: G06T5/002 ,  G06N3/088 ,  G06T7/11

    Abstract: Photorealistic image stylization concerns transferring style of a reference photo to a content photo with the constraint that the stylized photo should remain photorealistic. Examples of styles include seasons (summer, winter, etc.), weather (sunny, rainy, foggy, etc.), lighting (daytime, nighttime, etc.). A photorealistic image stylization process includes a stylization step and a smoothing step. The stylization step transfers the style of the reference photo to the content photo. A photo style transfer neural network model receives a photorealistic content image and a photorealistic style image and generates an intermediate stylized photorealistic image that includes the content of the content image modified according to the style image. A smoothing function receives the intermediate stylized photorealistic image and pixel similarity data and generates the stylized photorealistic image, ensuring spatially consistent stylizations.

    DYNAMIC PATH SELECTION FOR PROCESSING THROUGH A MULTI-LAYER NEURAL NETWORK
    15.
    发明申请
    DYNAMIC PATH SELECTION FOR PROCESSING THROUGH A MULTI-LAYER NEURAL NETWORK 有权

    公开(公告)号：US20250111222A1

    公开(公告)日：2025-04-03

    申请号：US18375377

    申请日：2023-09-29

    Applicant: NVIDIA Corporation

    Inventor： Zekun Hao ,  Ming-Yu Liu ,  Arun Mallya

    IPC: G06N3/08 ,  G06N3/04

    Abstract: Performance of a neural network is usually a function of the capacity, or complexity, of the neural network, including the depth of the neural network (i.e. the number of layers in the neural network) and/or the width of the neural network (i.e. the number of hidden channels). However, improving performance of a neural network by simply increasing its capacity has drawbacks, the most notable being the increased computational cost of a higher-capacity neural network. Since modern neural networks are configured such that the same neural network is evaluated regardless of the input, a higher capacity neural network means a higher computational cost incurred per input processed. The present disclosure provides for a multi-layer neural network that allows for dynamic path selection through the neural network when processing an input, which in turn can allow for increased neural network capacity without incurring the typical increased computation cost associated therewith.

Patent Agency Ranking