知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.027 seconds)

    Searching augmented reality experiences using visual embeddings
    1.
    发明授权
    Searching augmented reality experiences using visual embeddings 有权

    公开(公告)号：US12254049B2

    公开(公告)日：2025-03-18

    申请号：US18054420

    申请日：2022-11-10

    Applicant: Snap Inc.

    Inventor： Kevin Sarabia Dela Rosa ,  Adel Elmalaha ,  Kwot Sin Lee ,  Patrick Poirson

    IPC: G06F16/83 ,  G06F16/903 ,  G06F16/9035 ,  G06F16/907 ,  G06T19/00 ,  G06V10/74

    Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and a method for performing operations comprising: receiving an image from a client device; applying a machine learning model to the image to generate an embedding query vector, the machine learning model being trained to encode a plurality of images and text into a common embedding space; searching, based on the embedding query vector, a database of augmented reality (AR) experiences to identify a subset of AR experiences associated with one or more embeddings that correspond to the embedding query vector; and transmitting to the client device the subset of AR experiences associated with the one or more embeddings that correspond to the embedding query vector.

    MODEL FINE-TUNING FOR AUTOMATED AUGMENTED REALITY DESCRIPTIONS
    3.
    发明申请
    MODEL FINE-TUNING FOR AUTOMATED AUGMENTED REALITY DESCRIPTIONS 有权

    公开(公告)号：US20250148816A1

    公开(公告)日：2025-05-08

    申请号：US18502868

    申请日：2023-11-06

    Applicant: Snap Inc.

    Inventor： Maksim Gusarov ,  Kwot Sin Lee ,  Patrick Poirson ,  Chen Wang

    IPC: G06V20/70 ,  G06F40/40 ,  G06N3/0455 ,  G06T11/00 ,  G06V10/774 ,  G06V20/20 ,  G06V20/40

    Abstract: A second input image is generated by applying a target augmented reality (AR) effect to a first input image. The first input image and the second input image are provided to a first visual-semantic machine learning model to obtain output describing at least one feature of the target AR effect. The first visual-semantic machine learning model is fine-tuned from a second visual-semantic machine learning model by using training samples. Each training sample comprises a first training image, a second training image, and a training description of a given AR effect. The second training image is generated by applying the given AR effect to the first training image. A description of the target AR effect is selected based on the output of the visual-semantic machine learning model. The description of the target AR effect is stored in association with an identifier of the target AR effect.

    EMBEDDINGS REPRESENTING VISUAL AUGMENTATIONS
    6.
    发明公开
    EMBEDDINGS REPRESENTING VISUAL AUGMENTATIONS 审中-公开

    公开(公告)号：US20240355063A1

    公开(公告)日：2024-10-24

    申请号：US18304078

    申请日：2023-04-20

    Applicant: Snap Inc.

    Inventor： Zhenpeng Zhou ,  Patrick Poirson ,  Maksim Gusarov ,  Chen Wang ,  Oleg Tovstyi

    IPC: G06T19/00 ,  G06T1/00 ,  G06V10/74 ,  H04N5/262

    CPC classification number: G06T19/006 ,  G06T1/0021 ,  G06V10/761 ,  H04N5/2621

    Abstract: An input video item that includes a target visual augmentation is accessed. A machine learning model uses the input video item to generate an embedding. The embedding may comprise a vector representation of a visual effect of the target visual augmentation. The machine learning model is trained, in an unsupervised training phase, to minimize loss between training video representations generated within each of a plurality of training sets. Each training set comprises a plurality of different training video items that each include a predefined visual augmentation. Based on the generation of the embedding of the input video item, the target visual augmentation is mapped to an augmentation identifier.

Patent Agency Ranking