公开(公告)号：WO2022232005A1

公开(公告)日：2022-11-03

申请号：PCT/US2022/026107

申请日：2022-04-25

Applicant: SNAP INC.

Inventor： NIELSEN, Simon

IPC: B29C64/393 ,  B29C64/209 ,  B29C64/245 ,  B29C64/118 ,  B33Y10/00 ,  B33Y30/00 ,  B33Y50/02 ,  B33Y70/00 ,  B22F12/50 ,  B22F12/90

Abstract: A 3D item formed on a base having a cavity or void to form an anchor. An extruded filament of a heated material is first deposited into the cavity at a high temperature and high flow rate such that the material flows easier and fills the cavity and forms the anchor. After the cavity is filled such that the anchor is formed, the extrusion of the filament continues at a lower temperature and at a lower flow rate to form the 3D item upon the anchor. The extruded filament in the cavity and the 3D item are a unitary item.

公开(公告)号：WO2022213031A1

公开(公告)日：2022-10-06

申请号：PCT/US2022/071311

申请日：2022-03-24

Applicant: SNAP INC.

Inventor： KRISHNAN GORUMKONDA, Gurunandan

IPC: G10L21/007 ,  G06N3/04 ,  G06N3/08 ,  G06N3/0454 ,  G06N3/088 ,  G10L15/16 ,  G10L15/26 ,  G10L2021/0135 ,  G10L25/51

Abstract: A messaging system for audio character type swapping. Methods of audio character type swapping include receiving input audio data having a first characteristic and transforming the input audio data to an input image where the input image represents the frequencies and intensities of the audio. The methods further include processing the input image using a convolutional neural network (CNN) to generate an output image and transforming the output image to output audio data, the output audio data having a second characteristic. The input audio and output audio may include vocals. The first characteristics may indicate a male voice and the second characteristics may indicate a female voice. The CNN is trained together with another CNN that changes input audio having the second characteristic to audio having the first characteristic. The CNNs are trained using discriminator CNNs that determine whether audio has a first characteristic or a second characteristic.

公开(公告)号：WO2022213029A1

公开(公告)日：2022-10-06

申请号：PCT/US2022/071305

申请日：2022-03-24

Applicant: SNAP INC.

Inventor： GURGUL, Piotr ,  MAGASWERAN, Lucas, Rangit

IPC: G01C21/20 ,  G01S5/00 ,  H04W4/00 ,  H04W64/00

Abstract: Systems, methods, and computer readable media that schedules requests for location data of a mobile device, where the methods include selecting a first positioning system based on a power requirement, a latency requirement, and an accuracy requirement, and determining whether a first condition is satisfied for querying the first positioning system. The method further comprises in response to a determination that the first condition is satisfied, querying the first positioning system for first position data. The method further comprises in response to a determination that the first condition is not satisfied, selecting a second positioning system based on the power requirement, the latency requirement, and the accuracy requirement, determining whether a second condition is satisfied for querying the second positioning system, and in response to a determination that the second condition is satisfied, querying the second positioning system for second position data.

公开(公告)号：WO2022212257A1

公开(公告)日：2022-10-06

申请号：PCT/US2022/022148

申请日：2022-03-28

Applicant: SNAP INC.

Inventor： DEMIDOV, Nikita ,  GOLOBOKOV, Roman ,  MELNYK, Alina ,  VOSS, Jeremy, Baker ,  BROMOT, Aleksei

IPC: G06T11/00 ,  G06T11/60 ,  G06T19/006 ,  G06V10/82 ,  G06V40/166 ,  H04L51/21 ,  H04L51/52 ,  H04N2005/2726 ,  H04N5/272

Abstract: The subject technology receives at least one signal from a computing device, the at least one signal comprising at least one of a current time, battery power, sensor information, or location information. The subject technology generates a digital sticker, the digital sticker including graphical content indicating information based at least in part based on the at least one signal and media content including an image of a target face, the image of the target face being modified based on at least one of sets of source pose parameters to mimic at least one of positions of a head of a source actor and at least one of facial expressions of the source actor. The subject technology provides augmented reality content for display on a computing device, the augmented reality content including the digital sticker as an overlay on at least a portion of the augmented reality content.

公开(公告)号：WO2022212175A1

公开(公告)日：2022-10-06

申请号：PCT/US2022/021769

申请日：2022-03-24

Applicant: SNAP INC.

Inventor： POWELL, Alexander P. ,  THOMAS, Mark

IPC: G06F3/01 ,  G06F3/0488 ,  H04W4/21 ,  G06F3/016 ,  H04L67/131

Abstract: Method for generating haptic and audio feedback responses starts with processor causing communication interface for communication session to be displayed on first and second user interfaces. Communication interface includes first area and second area. Processor detects first touch input on first user interface and second touch input on second user interface and determines location of first touch input being in first area and location of second touch input being in second area. Processor causes first and second user interfaces to generate first audio feedback response associated with first area and second audio feedback response associated with second area. In response to determining that location of first touch input is updated to second area while the location of the second touch input is in second area, processor causes first and second user interfaces to generate enhanced audio feedback response and enhanced haptic response feedback. Other embodiments are described herein.

公开(公告)号：WO2022204674A1

公开(公告)日：2022-09-29

申请号：PCT/US2022/071250

申请日：2022-03-22

Applicant: SNAP INC.

Inventor： ASSOULINE, Avihay ,  BERGER, Itamar ,  LUO, Jean ,  ZOHAR, Matan

IPC: G06T19/00 ,  G06T7/00

Abstract: Methods and systems are disclosed for performing operations comprising: receiving, by one or more processors, an image that includes a depiction of a face of a user; computing a real-world scale of the face of the user based on a selected subset of landmarks of the face of the user; obtaining an augmented reality graphical element comprising augmented reality eyewear; scaling the augmented reality graphical element based on the computed real-world scale of the face; and positioning the scaled augmented reality graphical element within the image on the face of the user.

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.

公开(公告)号：WO2022147457A1

公开(公告)日：2022-07-07

申请号：PCT/US2021/073167

申请日：2021-12-29

Applicant: SNAP INC. ,  CANSIZOGLU, Omer ,  DOSHI, Chintan ,  LI, Yuechuan ,  MINAKOV, Stanislav ,  POLIAKOV, Fedir ,  WILDER, Justin

Inventor： CANSIZOGLU, Omer ,  DOSHI, Chintan ,  LI, Yuechuan ,  MINAKOV, Stanislav ,  POLIAKOV, Fedir ,  WILDER, Justin

IPC: G06T19/00 ,  G11B27/036 ,  G06V20/20 ,  G11B27/10 ,  G11B27/28

Abstract: The subject technology sends captured image data and metadata to a first set of computing processes for processing. The subject technology receives, asynchronously from a second set of computing processes, second metadata. The subject technology detects a signal indicating a command to stop image data capturing. The subject technology, in response to the detected signal, generating a composite AR content item based on the metadata and the captured image data. The subject technology provides the composite AR content item for rendering for display on an eyewear device.

公开(公告)号：WO2022147282A1

公开(公告)日：2022-07-07

申请号：PCT/US2021/065728

申请日：2021-12-30

Applicant: SNAP INC. ,  DESSERREY, Laurent ,  EIRINBERG, Dylan Shane ,  GRANTHAM, Matthew Colin

Inventor： DESSERREY, Laurent ,  EIRINBERG, Dylan Shane ,  GRANTHAM, Matthew Colin

IPC: G06F9/451 ,  G06F3/04817 ,  G06T19/00

Abstract: In one or more implementations, a user interface is displayed that includes user interface elements that correspond to third-party application resources that are executable within a client application. The user interface elements may be selectable to launch the third-party application resources within the client application. The user interface may be accessed from a camera user interface of the client application and the user interface may also have a region that includes a portion of the camera user interface in addition to the user interface elements that correspond to the third-party application resources.

公开(公告)号：WO2022146796A1

公开(公告)日：2022-07-07

申请号：PCT/US2021/064697

申请日：2021-12-21

Applicant: SNAP INC.

Inventor： ANVARIPOUR, Kaveh ,  BARRON, Christine ,  BOYD, Nathan Kenneth ,  HEIKKINEN, Christie Marie ,  LANKAGE, Ranidu ,  MORENO, Daniel ,  WARD, Shannon ,  WILLIAMS, Tabari

IPC: H04N21/4223 ,  G06Q50/00 ,  H04L51/10 ,  H04L51/52 ,  H04N21/4788 ,  H04N21/488 ,  H04N21/81

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for adding time-based captions to captured video. The program and method provide for displaying, by a messaging application, a preview user interface for previewing and editing captured video in order to generate a media content item, the preview user interface including an interface element which is selectable to switch to a captions user interface for adding a caption to the media content item; switching, in response to first user input selecting the interface element, to the captions user interface which is configured to receive user input for caption content and a duration to display the caption content; receiving, via the captions user interface, second user input for the caption content and the duration; and generating the media content item based on the caption content and the duration to display the caption content.