中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

55 records (took 0.021 seconds)

    ENCODING AND DECODING A STYLIZED CUSTOM GRAPHIC
    2.
    发明公开
    ENCODING AND DECODING A STYLIZED CUSTOM GRAPHIC 审中-公开

    公开(公告)号：US20230237706A1

    公开(公告)日：2023-07-27

    申请号：US18128128

    申请日：2023-03-29

    Applicant: Snap Inc.

    Inventor： Drake Austin Rehfeld ,  Rahul Bhupendra Sheth ,  Ning Zhang

    IPC: G06T9/00 ,  H04L51/52 ,  G06N3/047

    CPC classification number: G06T9/002 ,  H04L51/52 ,  G06N3/047

    Abstract: Disclosed are methods for encoding information in a graphic image. The information may be encoded so as to have a visual appearance that adopts a particular style, so that the encoded information is visually pleasing in the environment in which it is displayed. An encoder and decoder are trained during an integrated training process, where the encoder is tuned to minimize a loss when its encoded images are decoded. Similarly, the decoder is also trained to minimize loss when decoding the encoded images. Both the encoder and decoder may utilize a convolutional neural network in some aspects to analyze data and/or images. Once data is encoded, a style from a sample image is transferred to the encoded data. When decoding, the decoder may largely ignore the style aspects of the encoded data and decode based on a content portion of the data.

    FEEDBACK ADVERSARIAL LEARNING
    3.
    发明申请
    FEEDBACK ADVERSARIAL LEARNING 有权

    公开(公告)号：US20220327358A1

    公开(公告)日：2022-10-13

    申请号：US17808274

    申请日：2022-06-22

    Applicant: Snap Inc.

    Inventor： Jacob Minyoung Huh ,  Shao-Hua Sun ,  Ning Zhang

    IPC: G06N3/04 ,  G06V30/194 ,  G06N3/08

    Abstract: Disclosed is a feedback adversarial learning framework, a recurrent framework for generative adversarial networks that can be widely adapted to not only stabilize training but also generate higher quality images. In some aspects, a discriminator's spatial outputs are distilled to improve generation quality. The disclosed embodiments model the discriminator into the generator, and the generator learns from its mistakes over time. In some aspects, a discriminator architecture encourages the model to be locally and globally consistent.

    NEURAL NETWORK-BASED IMAGE STREAM MODIFICATION
    4.
    发明申请
    NEURAL NETWORK-BASED IMAGE STREAM MODIFICATION 有权

    公开(公告)号：US20220172448A1

    公开(公告)日：2022-06-02

    申请号：US17651524

    申请日：2022-02-17

    Applicant: Snap Inc.

    Inventor： Travis Chen ,  Samuel Edward Hare ,  Yuncheng Li ,  Tony Mathew ,  Jonathan Solichin ,  Jianchao Yang ,  Ning Zhang

    IPC: G06T19/20 ,  G06T7/20 ,  G06T19/00 ,  G06T7/73 ,  G06V10/20 ,  G06V20/20 ,  G06V20/40

    Abstract: Systems, devices, media, and methods are presented for object detection and inserting graphical elements into an image stream in response to detecting the object. The systems and methods detect an object of interest in received frames of a video stream. The systems and methods identify a bounding box for the object of interest and estimate a three-dimensional position of the object of interest based on a scale of the object of interest. The systems and methods generate one or more graphical elements having a size based on the scale of the object of interest and a position based on the three-dimensional position estimated for the object of interest. The one or more graphical elements are generated within the video stream to form a modified video stream. The systems and methods cause presentation of the modified video stream including the object of interest and the one or more graphical elements.

    ENCODING AND DECODING A STYLIZED CUSTOM GRAPHIC
    5.
    发明申请
    ENCODING AND DECODING A STYLIZED CUSTOM GRAPHIC 有权

    公开(公告)号：US20210256736A1

    公开(公告)日：2021-08-19

    申请号：US17302361

    申请日：2021-04-30

    Applicant: Snap Inc. Prefix

    Inventor： Drake Austin Rehfeld ,  Rahul Bhupendra Sheth ,  Ning Zhang

    IPC: G06T9/00 ,  H04L12/58 ,  G06N3/04

    Abstract: Disclosed are methods for encoding information in a graphic image. The information may be encoded so as to have a visual appearance that adopts a particular style, so that the encoded information is visually pleasing in the environment in which it is displayed. An encoder and decoder are trained during an integrated training process, where the encoder is tuned to minimize a loss when its encoded images are decoded. Similarly, the decoder is also trained to minimize loss when decoding the encoded images. Both the encoder and decoder may utilize a convolutional neural network in some aspects to analyze data and/or images. Once data is encoded, a style from a sample image is transferred to the encoded data. When decoding, the decoder may largely ignore the style aspects of the encoded data and decode based on a content portion of the data.

    NEURAL NETWORK-BASED IMAGE STREAM MODIFICATION
    6.
    发明申请
    NEURAL NETWORK-BASED IMAGE STREAM MODIFICATION 审中-公开

    公开(公告)号：US20200258313A1

    公开(公告)日：2020-08-13

    申请号：US15929374

    申请日：2020-04-29

    Applicant: Snap Inc.

    Inventor： Travis Chen ,  Samuel Edward Hare ,  Yuncheng Li ,  Tony Mathew ,  Jonathan Solichin ,  Jianchao Yang ,  Ning Zhang

    IPC: G06T19/20 ,  G06T7/20 ,  G06T19/00 ,  G06T7/73 ,  G06K9/32 ,  G06K9/00

    Abstract: Systems, devices, media, and methods are presented for object detection and inserting graphical elements into an image stream in response to detecting the object. The systems and methods detect an object of interest in received frames of a video stream. The systems and methods identify a bounding box for the object of interest and estimate a three-dimensional position of the object of interest based on a scale of the object of interest. The systems and methods generate one or more graphical elements having a size based on the scale of the object of interest and a position based on the three-dimensional position estimated for the object of interest. The one or more graphical elements are generated within the video stream to form a modified video stream. The systems and methods cause presentation of the modified video stream including the object of interest and the one or more graphical elements.

    ENCODING AND DECODING A STYLIZED CUSTOM GRAPHIC
    8.
    发明公开
    ENCODING AND DECODING A STYLIZED CUSTOM GRAPHIC 审中-公开

    公开(公告)号：US20240054687A1

    公开(公告)日：2024-02-15

    申请号：US18382729

    申请日：2023-10-23

    Applicant: Snap Inc.

    Inventor： Drake Austin Rehfeld ,  Rahul Bhupendra Sheth ,  Ning Zhang

    IPC: G06T9/00 ,  H04L51/52 ,  G06N3/047

    CPC classification number: G06T9/002 ,  H04L51/52 ,  G06N3/047

    Abstract: An example system includes an encoder configured to receive a bit string and encode the bit string into a visual representation, and a decoder configured to receive an image including the visual representation and decode the bit string from the visual representation. In some examples, the encoder and decoder are trained as a pair by obtaining a training bit string, encoding the training bit string into a training visual representation using the encoder, decoding the training visual representation using the decoder to generate a decoded bit string, determining an error between the training bit string and the decoded bit string, and updating parameters of the encoder and decoder to reduce the error.

Patent Agency Ranking