利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

13300 条记录 (耗时 0.044 秒)

    UTILIZING A DIFFUSION PRIOR NEURAL NETWORK FOR TEXT GUIDED DIGITAL IMAGE EDITING
    1.
    发明公开
    UTILIZING A DIFFUSION PRIOR NEURAL NETWORK FOR TEXT GUIDED DIGITAL IMAGE EDITING 审中-公开

    公开(公告)号：US20240362842A1

    公开(公告)日：2024-10-31

    申请号：US18308017

    申请日：2023-04-27

    申请人： Adobe Inc.

    发明人： Hareesh Ravi ,  Sachin Kelkar ,  Midhun Harikumar ,  Ajinkya Gorakhnath Kale

    IPC分类号： G06T11/60 ,  G06T5/00

    CPC分类号： G06T11/60 ,  G06T5/70 ,  G06T2200/24 ,  G06T2207/20084

    摘要： The present disclosure relates to systems, methods, and non-transitory computer readable media for utilizing a diffusion prior neural network for text guided digital image editing. For example, in one or more embodiments the disclosed systems utilize a text-image encoder to generate a base image embedding from the base digital image and an edit text embedding from edit text. Moreover, the disclosed systems utilize a diffusion prior neural network to generate a text-image embedding. In particular, the disclosed systems inject the base image embedding at a conceptual editing step of the diffusion prior neural network and condition a set of steps of the diffusion prior neural network after the conceptual editing step utilizing the edit text embedding. Furthermore, the disclosed systems utilize a diffusion neural network to create a modified digital image from the text-edited image embedding and the base image embedding.

    Systems and methods for automatically grouping design elements
    8.
    发明公开
    Systems and methods for automatically grouping design elements 审中-公开

    公开(公告)号：US20240346725A1

    公开(公告)日：2024-10-17

    申请号：US18752178

    申请日：2024-06-24

    申请人： Canva Pty Ltd

    发明人： Andrew James Stewart ,  Michelle Munn Wai Seeto

    IPC分类号： G06T11/60 ,  G06F40/103 ,  G06F40/106

    CPC分类号： G06T11/60 ,  G06F40/106 ,  G06F40/103

    摘要： Described herein is a computer implemented method for automatically grouping design elements on a page. The method includes: determining an initial set of design element groups; performing one or more design element grouping iterations, each including: calculating a set of pairwise relationship scores and determining, based on the set of pairwise relationship scores, whether any pairs of design element groups should be combined. In response to determining that a particular pair of design element groups should be combined the method further includes combining the particular pair of design element groups into a single design element group.

    METHOD AND SYSTEM FOR CREATING GROUP HIGHLIGHT REELS OF CONSUMERS CONSUMING MEDIA CONTENT AT DIFFERENT LOCATIONS/TIMES
    9.
    发明公开
    METHOD AND SYSTEM FOR CREATING GROUP HIGHLIGHT REELS OF CONSUMERS CONSUMING MEDIA CONTENT AT DIFFERENT LOCATIONS/TIMES 审中-公开

    公开(公告)号：US20240346720A1

    公开(公告)日：2024-10-17

    申请号：US18298834

    申请日：2023-04-11

    申请人： MOTOROLA MOBILITY LLC

    发明人： AMIT KUMAR AGRAWAL ,  KRISHNAN RAGHAVAN

    IPC分类号： G06T11/60 ,  G06T5/50 ,  H04N21/8547

    CPC分类号： G06T11/60 ,  G06T5/50 ,  H04N21/8547 ,  G06T2207/20221

    摘要： A method enables creation of group highlights for consumers consuming media content at different locations/times. The method includes initiating consumer experience collage generation on a first electronic device. The method includes receiving, via a network interface from at least one second electronic device that can operate in a consumer experiencing capturing (CEC) mode, one or more images and at least one of a portion of a first media content or an associated time marker identifying a presentation time of the portion within the first media content. The method includes, in response to receiving the associated time marker, accessing a copy of the first media content and retrieving, based on the associated time marker, the portion of the first media content from the copy. The method includes generating a composite product comprising a combination of the at least one image and the portion of the first media content.

    IMAGE MATCHING APPARATUS, CONTROL METHOD, AND NON-TRANSITORY COMPUTER-READABLE STORAGE MEDIUM
    10.
    发明公开
    IMAGE MATCHING APPARATUS, CONTROL METHOD, AND NON-TRANSITORY COMPUTER-READABLE STORAGE MEDIUM 审中-公开

    公开(公告)号：US20240338927A1

    公开(公告)日：2024-10-10

    申请号：US18580038

    申请日：2021-09-30

    申请人： NEC Corporation

    发明人： Royston Rodrigues ,  Masahiro Tani

    IPC分类号： G06V10/74 ,  G06T11/60 ,  G06V10/44

    CPC分类号： G06V10/761 ,  G06T11/60 ,  G06V10/44

    摘要： An image matching apparatus (2000) acquires a ground-view image (20), an aerial-view image (30), a ground depth image (40), and an aerial depth image (50). The ground depth image (40) indicates distance from a ground camera to each location captured in the ground-view image (20). The aerial depth image (50) indicates distance from a center location captured in the aerial-view image to each location captured in the aerial-view image (50). The image matching apparatus (2000) extracts features from the ground-view image and the ground depth image to compute ground feature (60), and extract features from the aerial-view image and the aerial depth image to compute aerial feature (70). The image matching apparatus (2000) determines whether or not the ground-view image (20) and the aerial-view image (30) match each other using the ground feature (60) and the aerial feature (70).