中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

79 records (took 0.029 seconds)

    NEURAL VECTOR FIELDS FOR 3D SHAPE GENERATION
    1.
    发明公开
    NEURAL VECTOR FIELDS FOR 3D SHAPE GENERATION 审中-公开

    公开(公告)号：US20240193887A1

    公开(公告)日：2024-06-13

    申请号：US18361587

    申请日：2023-07-28

    Applicant: NVIDIA Corporation

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

    IPC: G06T19/20

    CPC classification number: G06T19/20 ,  G06F30/10 ,  G06T2210/56 ,  G06T2219/2021

    Abstract: Synthesis of high-quality 3D shapes with smooth surfaces has various creative and practical use cases, such as 3D content creation and CAD modeling. A vector field decoder neural network is trained to predict a generative vector field (GVF) representation of a 3D shape from a latent representation (latent code or feature volume) of the 3D shape. The GVF representation is agnostic to surface orientation, all dimensions of the vector field vary smoothly, the GVF can represent both watertight and non-watertight 3D shapes, and there is a one-to-one mapping between a predicted 3D shape and the ground truth 3D shape (i.e., the mapping is bijective). The vector field decoder can synthesize 3D shapes in multiple categories and can also synthesize 3D shapes for objects that were not included in the training dataset. In other words, the vector field decoder is also capable of zero-shot generation.

    FRAME SELECTION FOR STREAMING APPLICATIONS
    4.
    发明公开
    FRAME SELECTION FOR STREAMING APPLICATIONS 审中-公开

    公开(公告)号：US20240114162A1

    公开(公告)日：2024-04-04

    申请号：US17955734

    申请日：2022-09-29

    Applicant: Nvidia Corporation

    Inventor： Aurobinda Maharana ,  Arun Mallya ,  Ming-Yu Liu ,  Abhijit Patait

    IPC: H04N19/50 ,  H04N19/21

    CPC classification number: H04N19/50 ,  H04N19/21

    Abstract: Systems and methods herein address reference frame selection in video streaming applications using one or more processing units to decode a frame of an encoded video stream that uses an inter-frame depicting an object and an intra-frame depicting the object, the intra-frame being included in a set of intra-frames based at least in part on at least one attribute of the object as depicted in the intra-frame being different from the at least one attribute of the object as depicted in other intra-frames of the set of intra-frames.

    TRAINING A NEURAL NETWORK TO PREDICT SUPERPIXELS USING SEGMENTATION-AWARE AFFINITY LOSS
    7.
    发明申请
    TRAINING A NEURAL NETWORK TO PREDICT SUPERPIXELS USING SEGMENTATION-AWARE AFFINITY LOSS 审中-公开

    公开(公告)号：US20200334502A1

    公开(公告)日：2020-10-22

    申请号：US16921012

    申请日：2020-07-06

    Applicant: NVIDIA Corporation

    Inventor： Wei-Chih Tu ,  Ming-Yu Liu ,  Varun Jampani ,  Deqing Sun ,  Ming-Hsuan Yang ,  Jan Kautz

    IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06T7/11

    Abstract: Segmentation is the identification of separate objects within an image. An example is identification of a pedestrian passing in front of a car, where the pedestrian is a first object and the car is a second object. Superpixel segmentation is the identification of regions of pixels within an object that have similar properties. An example is identification of pixel regions having a similar color, such as different articles of clothing worn by the pedestrian and different components of the car. A pixel affinity neural network (PAN) model is trained to generate pixel affinity maps for superpixel segmentation. The pixel affinity map defines the similarity of two points in space. In an embodiment, the pixel affinity map indicates a horizontal affinity and vertical affinity for each pixel in the image. The pixel affinity map is processed to identify the superpixels.

    Training a neural network to predict superpixels using segmentation-aware affinity loss
    8.
    发明授权
    Training a neural network to predict superpixels using segmentation-aware affinity loss 有权

    公开(公告)号：US10748036B2

    公开(公告)日：2020-08-18

    申请号：US16188641

    申请日：2018-11-13

    Applicant: NVIDIA Corporation

    Inventor： Wei-Chih Tu ,  Ming-Yu Liu ,  Varun Jampani ,  Deqing Sun ,  Ming-Hsuan Yang ,  Jan Kautz

    IPC: G06K9/00 ,  G06T7/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06T7/11

    Abstract: Segmentation is the identification of separate objects within an image. An example is identification of a pedestrian passing in front of a car, where the pedestrian is a first object and the car is a second object. Superpixel segmentation is the identification of regions of pixels within an object that have similar properties An example is identification of pixel regions having a similar color, such as different articles of clothing worn by the pedestrian and different components of the car. A pixel affinity neural network (PAN) model is trained to generate pixel affinity maps for superpixel segmentation. The pixel affinity map defines the similarity of two points in space. In an embodiment, the pixel affinity map indicates a horizontal affinity and vertical affinity for each pixel in the image. The pixel affinity map is processed to identify the superpixels.

    METHOD FOR FEW-SHOT UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION
    9.
    发明申请
    METHOD FOR FEW-SHOT UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION 审中-公开

    公开(公告)号：US20200242736A1

    公开(公告)日：2020-07-30

    申请号：US16261395

    申请日：2019-01-29

    Applicant: Nvidia Corporation

    Inventor： Ming-Yu Liu ,  Xun Huang ,  Tero Karras ,  Timo Aila ,  Jaakko Lehtinen

    IPC: G06T3/60 ,  G06T3/00 ,  G06K9/62 ,  G06T7/73

    Abstract: A few-shot, unsupervised image-to-image translation (“FUNIT”) algorithm is disclosed that accepts as input images of previously-unseen target classes. These target classes are specified at inference time by only a few images, such as a single image or a pair of images, of an object of the target type. A FUNIT network can be trained using a data set containing images of many different object classes, in order to translate images from one class to another class by leveraging few input images of the target class. By learning to extract appearance patterns from the few input images for the translation task, the network learns a generalizable appearance pattern extractor that can be applied to images of unseen classes at translation time for a few-shot image-to-image translation task.

    GUIDED HALLUCINATION FOR MISSING IMAGE CONTENT USING A NEURAL NETWORK
    10.
    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.

Patent Agency Ranking