公开(公告)号：US11922111B2

公开(公告)日：2024-03-05

申请号：US17988547

申请日：2022-11-16

Applicant: SNAP INC.

Inventor： Sagi Katz ,  Ilya Levin

IPC: G06F40/149 ,  G06F16/13 ,  G06F16/172 ,  G06F40/109 ,  H04L51/046

CPC classification number: G06F40/109 ,  G06F16/13 ,  G06F16/172 ,  H04L51/046

Abstract: Methods and system for creating and managing personalized fonts. Personalized fonts are created by applying personalization parameters to a base font using a style application method or module such as a neural style transformation. The personalized fonts may be transferred to recipients of textual communications to enable the recipient to read messages from a sender in the personalized font of the sender.

公开(公告)号：US20240029302A1

公开(公告)日：2024-01-25

申请号：US18373554

申请日：2023-09-27

Applicant: Snap Inc.

Inventor： Sagi Katz ,  Matthias Kalkgruber

IPC: G06T7/73 ,  G06T7/593 ,  G06T7/33 ,  G06T19/00

CPC classification number: G06T7/74 ,  G06T7/593 ,  G06T7/33 ,  G06T19/006 ,  H04N13/239

Abstract: A method for correcting a bending of a flexible device is described. In one aspect, the method includes accessing feature data of a first stereo frame that is generated by stereo optical sensors of the flexible device, the feature data generated based on a visual-inertial odometry (VIO) system of the flexible device, accessing depth map data of the first stereo frame, the depth map data generated based on a depth map system of the flexible device, estimating a pitch-roll bias and a yaw bias based on the features data and the depth map data of the first stereo frame, and generating a second stereo frame after the first stereo frame, the second stereo frame based on the pitch-roll bias and the yaw bias of the first stereo frame.

公开(公告)号：US20230412779A1

公开(公告)日：2023-12-21

申请号：US18229535

申请日：2023-08-02

Applicant: Snap Inc.

Inventor： Sagi Katz

IPC: H04N9/31 ,  G02B27/01 ,  G06F1/16

CPC classification number: H04N9/3114 ,  G02B27/0172 ,  H04N9/3155 ,  G02B2027/0178 ,  G06F1/1643 ,  H04N9/3182 ,  H04N9/3185

Abstract: A photo filter (e.g., artistic) light field effect system comprises an eyewear device that includes a frame, a temple connected to a lateral side of the frame, and a depth-capturing camera. Execution of programming by a processor configures the photo filter light field effect system to apply a photo filter selection to: (i) a left raw image or a left processed image to create a left photo filter image, and (ii) a right raw image or a right processed image to create a right photo filter image. The photo filter light field effect system generates, a photo filter light field effect image with an appearance of a spatial rotation or movement, by blending together the left photo filter image and the right photo filter image based on a left image disparity map and a right image disparity map.

公开(公告)号：US11792379B2

公开(公告)日：2023-10-17

申请号：US17684113

申请日：2022-03-01

Applicant: Snap Inc.

Inventor： Sagi Katz

IPC: H04N7/18 ,  H04N13/122 ,  G06T19/20 ,  H04N13/128 ,  H04N13/344 ,  H04N13/383 ,  G06T7/593 ,  G02B27/01 ,  G06T15/20 ,  H04N13/388

CPC classification number: H04N13/122 ,  G02B27/0172 ,  G02B27/0176 ,  G06T7/593 ,  G06T15/205 ,  G06T19/20 ,  H04N13/128 ,  H04N13/344 ,  H04N13/383 ,  H04N13/388 ,  G02B2027/0178

Abstract: A depth sculpturing system comprises an eyewear device that includes a frame, a temple connected to a lateral side of the frame, and a depth-capturing camera. The depth sculpturing system further includes a user input device. Execution of programming by a processor configures the depth sculpturing system to perform functions to track, via the user input device, motion of a two-dimensional input selection from an initial touch point to a final touch point. The depth sculpturing system determines a rotation matrix between an initial ray and a final ray that project to the initial touch point and the final touch point, correspondingly. The depth sculpturing system generates a depth sculptured image by applying the rotation matrix to vertices of an initial depth image. The depth sculpturing system presents, via an image display, the depth sculptured image.

公开(公告)号：US11589024B2

公开(公告)日：2023-02-21

申请号：US17346354

申请日：2021-06-14

Applicant: Snap Inc.

Inventor： Sagi Katz

IPC: H04N13/332 ,  G06F3/048 ,  H04N13/111 ,  H04N5/262 ,  H04N13/128 ,  G06T19/00 ,  G06F3/0488 ,  H04N13/00

Abstract: A photo filter (e.g., multi-dimensional) light field effect system includes an eyewear device having a frame, a temple connected to a lateral side of the frame, and a depth-capturing camera. Execution of programming by a processor configures the system to create an image in each of a least two dimensions and create a multi-dimensional light field effect image with an appearance of a spatial rotation or movement and transitional change, by blending together a left photo filter image and a right photo filter image in each dimension and blending the blended images from all dimensions.

公开(公告)号：US20220374505A1

公开(公告)日：2022-11-24

申请号：US17489394

申请日：2021-09-29

Applicant: Snap Inc.

Inventor： Sagi Katz

IPC: G06F21/32 ,  H04N13/344 ,  G06T7/593 ,  G06F1/16

Abstract: A method for generating reference biometric data based on a bending of a flexible device is described. In one aspect, a method includes forming training data includes bending estimates of a flexible device worn by a first user, training a model based on the training data, and generating reference biometric data for the first user based on the model.

公开(公告)号：US10776899B2

公开(公告)日：2020-09-15

申请号：US16558777

申请日：2019-09-03

Applicant: Snap Inc.

Inventor： Sagi Katz ,  Eyal Zak

IPC: H04N7/18 ,  G06T3/00 ,  H04N13/398 ,  H04N13/207 ,  G06F3/01 ,  H04N13/332 ,  H04N13/239 ,  H04B1/3827

Abstract: A virtual shockwave creation system comprises an eyewear device that includes a frame, a temple connected to a lateral side of the frame, and a depth-capturing camera. Execution of programming by a processor configures the virtual shockwave creation system to generate, for each of multiple initial depth images, a respective shockwave image by applying a transformation function to the initial three-dimensional coordinates. The virtual shockwave creation system creates a warped shockwave video including a sequence of the generated warped shockwave images. The virtual shockwave creation system presents, via an image display, the warped shockwave video.

公开(公告)号：US10764556B2

公开(公告)日：2020-09-01

申请号：US16561127

申请日：2019-09-05

Applicant: Snap Inc.

Inventor： Sagi Katz

IPC: H04N7/18 ,  H04N13/122 ,  G06T19/20 ,  H04N13/128 ,  H04N13/344 ,  H04N13/383 ,  G06T7/593 ,  G02B27/01 ,  G06T15/20 ,  H04N13/388

Abstract: A depth sculpturing system comprises an eyewear device that includes a frame, a temple connected to a lateral side of the frame, and a depth-capturing camera. The depth sculpturing system further includes a user input device. Execution of programming by a processor configures the depth sculpturing system to perform functions to track, via the user input device, motion of a two-dimensional input selection from an initial touch point to a final touch point. The depth sculpturing system determines a rotation matrix between an initial ray and a final ray that project to the initial touch point and the final touch point, correspondingly. The depth sculpturing system generates a depth sculptured image by applying the rotation matrix to vertices of an initial depth image. The depth sculpturing system presents, via an image display, the depth sculptured image.

公开(公告)号：US12260588B2

公开(公告)日：2025-03-25

申请号：US18373554

申请日：2023-09-27

Applicant: Snap Inc.

Inventor： Sagi Katz ,  Matthias Kalkgruber

IPC: G06T7/33 ,  G06T7/593 ,  G06T7/73 ,  G06T19/00 ,  H04N13/239

Abstract: A method for correcting a bending of a flexible device is described. In one aspect, the method includes accessing feature data of a first stereo frame that is generated by stereo optical sensors of the flexible device, the feature data generated based on a visual-inertial odometry (VIO) system of the flexible device, accessing depth map data of the first stereo frame, the depth map data generated based on a depth map system of the flexible device, estimating a pitch-roll bias and a yaw bias based on the features data and the depth map data of the first stereo frame, and generating a second stereo frame after the first stereo frame, the second stereo frame based on the pitch-roll bias and the yaw bias of the first stereo frame.

公开(公告)号：US12229977B2

公开(公告)日：2025-02-18

申请号：US17529527

申请日：2021-11-18

Applicant: Snap Inc.

Inventor： Georgios Evangelidis ,  Branislav Micusik ,  Sagi Katz

IPC: G06T7/50 ,  G06F3/01 ,  G06T3/18 ,  G06T19/00

Abstract: A method for AR-guided depth estimation is described. The method includes identifying a virtual object rendered in a first frame that is generated based on a first pose of an augmented reality (AR) device, determining a second pose of the AR device, the second pose following the first pose, identifying an augmentation area in the second frame based on the virtual object rendered in the first frame, and the second pose, determining depth information for the augmentation area in the second frame, and rendering the virtual object in the second frame based on the depth information.