公开(公告)号：US20240362874A1

公开(公告)日：2024-10-31

申请号：US18767039

申请日：2024-07-09

申请人： Snap Inc.

发明人： Avihay Assouline ,  Itamar Berger ,  Gal Dudovitch ,  Peleg Harel ,  Ma'ayan Mishin Shuvi

IPC分类号： G06T19/00 ,  G06N3/082 ,  G06Q30/0601

CPC分类号： G06T19/006 ,  G06N3/082 ,  G06Q30/0643 ,  G06T2200/08 ,  G06T2200/24 ,  G06T2210/16 ,  G06T2219/024

摘要： Aspects of the present disclosure involve a system for providing AR experiences. The system accesses, by a messaging application, an image depicting a real-world fashion item of a user and generates a three-dimensional (3D) virtual fashion item based on the real-world fashion item depicted in the image. The system stores the 3D virtual fashion item in a database that includes a virtual wardrobe comprising a plurality of 3D virtual fashion items associated with the user. The system generates, by the messaging application, an augmented reality (AR) experience that allows the user to interact with the virtual wardrobe.

公开(公告)号：US20240362863A1

公开(公告)日：2024-10-31

申请号：US18764665

申请日：2024-07-05

申请人： Snap Inc.

发明人： Piers George Cowburn ,  David Li ,  Isac Andreas Muller Sandvik ,  Qi Pan

IPC分类号： G06T17/05 ,  H04L51/046 ,  H04L67/306 ,  H04W4/02

CPC分类号： G06T17/05 ,  H04L51/046 ,  H04L67/306 ,  H04W4/023

摘要： A location-based augmented-reality system to generate and cause display of augmented-reality content that includes three-dimensional typography, based on a perspective, and location of a client device.

公开(公告)号：US20240361615A1

公开(公告)日：2024-10-31

申请号：US18664930

申请日：2024-05-15

申请人： Snap Inc.

发明人： Ugur Olgun ,  Patrick Kusbel ,  Russell Douglas Patton ,  Jonathan M. Ridriguez, II ,  Patrick Timothy McSweeney Simons

IPC分类号： G02C11/00 ,  G06Q20/32 ,  H01Q1/27 ,  H01Q5/50 ,  H01Q7/00 ,  H02J50/10 ,  H04B1/18 ,  H04B1/3827 ,  H04B5/24 ,  H04B5/72

CPC分类号： G02C11/10 ,  H01Q1/273 ,  H01Q7/00 ,  H02J50/10 ,  H04B1/18 ,  H04B1/385 ,  H04B5/24 ,  H04B5/72 ,  G06Q20/3278 ,  H01Q5/50

摘要： Apparatuses and systems for wearable devices such as eyewear are described. According to one embodiment, the wearable device includes a frame, onboard electronics components, and an antenna disposed around an eyepiece area of the frame that is configured to hold an optical element. The antenna is configured for inductive coupling. In some embodiments, a switch coupled to the antenna allows selection between circuitry for inductive charging of a battery and near-field communication (NFC) circuitry for communicating data via the antenna.

公开(公告)号：US12131448B2

公开(公告)日：2024-10-29

申请号：US17937734

申请日：2022-10-03

申请人： Snap Inc.

发明人： Gal Dudovitch ,  Peleg Harel ,  Ma'ayan Mishin Shuvi ,  Gal Sasson ,  Matan Zohar

IPC分类号： G06T5/77 ,  G06T5/50 ,  G06T7/11 ,  G06T7/20 ,  G06T11/00

CPC分类号： G06T5/77 ,  G06T5/50 ,  G06T7/11 ,  G06T7/20 ,  G06T11/00 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221 ,  G06T2207/30196 ,  G06T2207/30244

摘要： Aspects of the present disclosure involve a system for performing real-time in-painting using machine learning techniques. The system receives a video that includes a depiction of a real-world object in a real-world environment. The system accesses a segmentation associated with the real-world object and removes a depiction of the real-world object from a region of a first frame of the video. The system processes, by a machine learning model, the first frame and one or more previous frames of the video that precede the first frame to generate a new frame in which portions of the first frame have been blended into the region from which the depiction of the real-world object has been removed.

公开(公告)号：US12131003B2

公开(公告)日：2024-10-29

申请号：US18196915

申请日：2023-05-12

申请人： Snap Inc.

发明人： Daniel Amitay ,  Jonathan Brody ,  Maxwell Gale ,  Timothy Jordan Garcia ,  Daniel Vincent Grippi ,  Jeffrey Arthur Johnson ,  Sheridan Kates ,  Andrew Lin ,  Walton Lin ,  Gaurav Misra ,  Suraj Vindana Samaranayake ,  Amer Shahnawaz ,  Evan Spiegel

IPC分类号： G06F3/04817 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/0488 ,  G06F16/248 ,  G06F16/29 ,  G06F16/487 ,  G06F16/9535 ,  G06F16/9537 ,  G06Q50/00 ,  G06T11/20 ,  G06T11/60 ,  H04L9/40 ,  H04L41/22 ,  H04L41/28 ,  H04L51/52 ,  H04L67/12 ,  H04L67/306 ,  H04L67/50 ,  H04L67/52 ,  H04W4/02 ,  H04W4/029 ,  H04W4/18 ,  H04W4/21 ,  H04W12/02 ,  G06F9/54

CPC分类号： G06F3/04817 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/0488 ,  G06F16/248 ,  G06F16/29 ,  G06F16/487 ,  G06F16/9535 ,  G06F16/9537 ,  G06Q50/01 ,  G06T11/206 ,  G06T11/60 ,  H04L41/22 ,  H04L41/28 ,  H04L51/52 ,  H04L63/101 ,  H04L63/107 ,  H04L67/12 ,  H04L67/306 ,  H04L67/52 ,  H04L67/535 ,  H04W4/02 ,  H04W4/029 ,  H04W4/185 ,  H04W4/21 ,  H04W12/02 ,  G06F9/547 ,  G06T2200/24

摘要： A map-based graphical user interface (GUI) for a public messaging platform allows a user location-based to their own expired ephemeral content. Such expired content is no longer available to other users for online viewing. The user can, however, switch the GUI between a live mode and a historical mode, access to their own expired content in the historical mode being facilitated in a manner closely similar to that for viewing live publicly available content.

公开(公告)号：US20240355072A1

公开(公告)日：2024-10-24

申请号：US18760982

申请日：2024-07-01

申请人： Snap Inc.

发明人： Jean Luo ,  Ibram Uppal

IPC分类号： G06T19/00 ,  G06Q30/0601 ,  G06T17/00 ,  G06T19/20

CPC分类号： G06T19/006 ,  G06T17/00 ,  G06T19/20 ,  G06Q30/0603 ,  G06Q30/0643

摘要： The subject technology receives information for a product. The subject technology generates a 3D model file of the product in a first format. The subject technology converts the 3D model file to a 3D object file in a second format. The subject technology associates the 3D object file to the product in a product catalog service. The subject technology publishes an augmented reality (AR) content generator corresponding to the product.

公开(公告)号：US20240355064A1

公开(公告)日：2024-10-24

申请号：US18497629

申请日：2023-10-30

申请人： Snap Inc.

发明人： Daria Skrypnyk ,  Matthew Hallberg

IPC分类号： G06T19/00 ,  G06T15/04 ,  G06T17/20 ,  G06T19/20 ,  G10L15/18 ,  G10L15/22

CPC分类号： G06T19/006 ,  G06T15/04 ,  G06T17/20 ,  G06T19/20 ,  G10L15/1815 ,  G10L15/22 ,  G06T2219/2004 ,  G06T2219/2012 ,  G10L2015/223

摘要： Described is a system for overlaying visual content onto a real-world object by identifying a prompt of a user indicating a user's intent, accessing an image template, wherein the image template includes placement of features within the image template, and processing a combination of data associated with the image template and the prompt using a generative machine learning model to generate a first populated image template in which one or more portions of the image template are populated with visual content representing the user's intent. The system then proceeds to access an image depicting a real-world object and overlay the first populated image template that includes the visual content representative of the user's intent on at least a portion of the real-world object based on the placement of the features of the image template.

公开(公告)号：US20240355063A1

公开(公告)日：2024-10-24

申请号：US18304078

申请日：2023-04-20

申请人： Snap Inc.

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

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

CPC分类号： G06T19/006 ,  G06T1/0021 ,  G06V10/761 ,  H04N5/2621

摘要： 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.

公开(公告)号：US20240355019A1

公开(公告)日：2024-10-24

申请号：US18304181

申请日：2023-04-20

申请人： Snap Inc.

发明人： Avihay Assouline ,  Itamar Berger ,  Jonathan Heimann

IPC分类号： G06T11/60 ,  G06F40/20 ,  G06F40/40 ,  G06T7/10 ,  G06T7/60 ,  G06T11/00 ,  G06V10/776 ,  G06V20/20

CPC分类号： G06T11/60 ,  G06F40/20 ,  G06F40/40 ,  G06T7/10 ,  G06T7/60 ,  G06T11/001 ,  G06V10/776 ,  G06V20/20 ,  G06T2200/24 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20092 ,  G06T2207/20132 ,  G06T2207/30201 ,  G06T2210/16 ,  G06T2210/22

摘要： Methods and systems are disclosed for generating an extended reality (XR) try-on experience based on an image produced by a diffusion model. The system receives an image depicting a real-world object and generates a prompt comprising a textual description of a fashion item. The system analyzes the image and the textual description of the fashion item using a generative machine learning model to generate an artificial image that depicts an artificial object that resembles the real-world object wearing an artificial fashion item matching the textual description of the fashion item. The system identifies an object comprising a real-world product image that matches visual attributes of the artificial fashion item and replaces the artificial fashion item in the artificial image with the object to generate an output image.

公开(公告)号：US20240354641A1

公开(公告)日：2024-10-24

申请号：US18613645

申请日：2024-03-22

申请人： Snap Inc.

发明人： William Miles Miller ,  Aleksei Stoliar

IPC分类号： G06N20/00

CPC分类号： G06N20/00

摘要： Described is a system for gathering interaction data from use of one or more interaction functions by a first user, wherein the interaction data includes data in different modalities and generating a multimodal memory for the interaction data by applying the interaction data to a first machine learning model. The system also identifies a prompt for the first user and processes a combination of data associated with the prompt and the multimodal memory using a second machine learning model to generate recommended content for the first user. The system then proceeds to apply the recommended content to a first interaction client of the first user.