中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

19 records (took 0.022 seconds)

    SELECTING REPRESENTATIVE VIDEO FRAME BY MACHINE LEARNING
    1.
    发明申请
    SELECTING REPRESENTATIVE VIDEO FRAME BY MACHINE LEARNING 审中-公开

    公开(公告)号：WO2022146707A1

    公开(公告)日：2022-07-07

    申请号：PCT/US2021/063823

    申请日：2021-12-16

    Applicant: SNAP INC.

    Inventor： KOPPARAPU, Kavya Venkata Kota ,  DODSON, Benjamin ,  DRUDIS RIUS, Francesc, Xavier ,  KONG, Angus ,  LEIDER, Richard ,  REN, Jian ,  TULYAKOV, Sergey ,  YU, Jiayao

    IPC: G06V20/30 ,  G06V20/70

    Abstract: Aspects of the present disclosure involve a system comprising a medium storing a program and method for machine-learning based selection of a representative video frame. The program and method provide for receiving a set of video frames; determining a first subset of frames by removing frames outside of an image quality threshold; determining a second subset by removing frames outside of an image stillness threshold; computing feature data for each frame in the second subset; providing, for each frame in the second subset, the feature data to a machine learning model (MLM), the MLM being configured to output a score for each frame in the second subset of frames based on the feature data, the MLM having been trained with a first set of images labeled based on aesthetics, and with a second set of images labeled based on image quality; and selecting a frame based on output scores.

    CROSS-DOMAIN NEURAL NETWORKS FOR SYNTHESIZING IMAGE WITH FAKE HAIR COMBINED WITH REAL IMAGE
    2.
    发明申请
    CROSS-DOMAIN NEURAL NETWORKS FOR SYNTHESIZING IMAGE WITH FAKE HAIR COMBINED WITH REAL IMAGE 审中-公开

    公开(公告)号：WO2022047463A1

    公开(公告)日：2022-03-03

    申请号：PCT/US2021/071239

    申请日：2021-08-20

    Applicant: SNAP INC.

    Inventor： BONDICH, Artem ,  CHAI, Menglei ,  PYSHCHENKO, Oleksandr ,  REN, Jian ,  TULYAKOV, Sergey

    IPC: G06K9/00 ,  G06N3/04 ,  G06N3/08 ,  G06T7/00 ,  G06T11/00 ,  G06T17/00

    Abstract: A messaging system performs neural network hair rendering for images provided by users of the messaging system. A method of neural network hair rendering includes processing a three-dimensional (3D) model of fake hair and a first real hair image depicting a first person to generate a fake hair structure, and encoding, using a fake hair encoder neural subnetwork, the fake hair structure to generate a coded fake hair structure. The method further includes processing, using a cross-domain structure embedding neural subnetwork, the coded fake hair structure to generate a fake and real hair structure, and encoding, using an appearance encoder neural subnetwork, a second real hair image depicting a second person having a second head to generate an appearance map. The method further includes processing, using a real appearance renderer neural subnetwork, the appearance map and the fake and real hair structure to generate a synthesized real image.

    COMPRESSING IMAGE-TO-IMAGE MODELS WITH AVERAGE SMOOTHING
    3.
    发明申请
    COMPRESSING IMAGE-TO-IMAGE MODELS WITH AVERAGE SMOOTHING 审中-公开

    公开(公告)号：WO2022187086A1

    公开(公告)日：2022-09-09

    申请号：PCT/US2022/017865

    申请日：2022-02-25

    Applicant: SNAP INC.

    Inventor： REN, Jian ,  CHAI, Menglei ,  TULYAKOV, Sergey ,  JIN, Qing

    IPC: G06N3/08 ,  H04N19/90 ,  G06T9/00 ,  G06T11/00

    Abstract: System and methods for compressing image-to-image models. Generative Adversarial Networks (GANs) have achieved success in generating high-fidelity images. An image compression system and method adds a novel variant to class-dependent parameters (CLADE), referred to as CLADE-Avg, which recovers the image quality without introducing extra computational cost. An extra layer of average smoothing is performed between the parameter and normalization layers. Compared to CLADE, this image compression system and method smooths abrupt boundaries, and introduces more possible values for the scaling and shift. In addition, the kernel size for the average smoothing can be selected as a hyperparameter, such as a 3 x 3 kernel size. This method does not introduce extra multiplications but only addition, and thus does not introduce much computational overhead, as the division can be absorbed into the parameters after training.

    VIDEO SYNTHESIS WITHIN A MESSAGING SYSTEM
    4.
    发明申请
    VIDEO SYNTHESIS WITHIN A MESSAGING SYSTEM 审中-公开

    公开(公告)号：WO2022072725A1

    公开(公告)日：2022-04-07

    申请号：PCT/US2021/053012

    申请日：2021-09-30

    Applicant: SNAP INC.

    Inventor： CHAI, Menglei ,  OLSZEWSKI, Kyle ,  REN, Jian ,  TIAN, Yu ,  TULYAKOV, Sergey

    IPC: G06T11/00

    Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for video synthesis. The program and method provide for accessing a primary generative adversarial network (GAN) comprising a pre-trained image generator, a motion generator comprising a plurality of neural networks, and a video discriminator; generating an updated GAN based on the primary GAN, by performing operations comprising identifying input data of the updated GAN, the input data comprising an initial latent code and a motion domain dataset, training the motion generator based on the input data, and adjusting weights of the plurality of neural networks of the primary GAN based on an output of the video discriminator; and generating a synthesized video based on the primary GAN and the input data.

    FLOW-GUIDED MOTION RETARGETING
    6.
    发明申请
    FLOW-GUIDED MOTION RETARGETING 审中-公开

    公开(公告)号：WO2022146772A1

    公开(公告)日：2022-07-07

    申请号：PCT/US2021/064531

    申请日：2021-12-21

    Applicant: SNAP INC.

    Inventor： REN, Jian ,  CHAI, Menglei ,  WOODFORD, Oliver ,  OLSZEWSKI, Kyle ,  TULYAKOV, Sergey

    IPC: G06T13/40 ,  G06N3/02

    Abstract: Systems and methods herein describe a motion retargeting system. The motion retargeting system accesses a plurality of two-dimensional images comprising a person performing a plurality of body poses, extracts a plurality of implicit volumetric representations from the plurality of body poses, generates a three-dimensional warping field, the three-dimensional warping field configured to warp the plurality of implicit volumetric representations from a canonical pose to a target pose, and based on the three-dimensional warping field, generates a two-dimensional image of an artificial person performing the target pose.

    MOTION REPRESENTATIONS FOR ARTICULATED ANIMATION
    7.
    发明申请
    MOTION REPRESENTATIONS FOR ARTICULATED ANIMATION 审中-公开

    公开(公告)号：WO2022006299A1

    公开(公告)日：2022-01-06

    申请号：PCT/US2021/039935

    申请日：2021-06-30

    Applicant: SNAP INC.

    Inventor： CHAI, Menglei ,  REN, Jian ,  SIAROHIN, Aliaksandr ,  TULYAKOV, Sergey ,  WOODFORD, Oliver

    IPC: G06T13/80 ,  G06T7/00 ,  G06N3/0454 ,  G06N3/08 ,  G06T11/001 ,  G06T13/00 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T7/20

    Abstract: Systems and methods herein describe novel motion representations for animating articulated objects consisting of distinct parts. The described systems and method access source image data, identify driving image data to modify image feature data in the source image sequence data, generate, using an image transformation neural network, modified source image data comprising a plurality of modified source images depicting modified versions of the image feature data, the image transformation neural network being trained to identify, for each image in the source image data, a driving image from the driving image data, the identified driving image being implemented by the image transformation neural network to modify a corresponding source image in the source image data using motion estimation differences between the identified driving image and the corresponding source image, and stores the modified source image data.

Patent Agency Ranking