-
公开(公告)号:US20200242812A1
公开(公告)日:2020-07-30
申请号:US16846949
申请日:2020-04-13
Applicant: Snap Inc.
Inventor: Drake Austin Rehfeld , Rahul Bhupendra Sheth , Ning Zhang
Abstract: Disclosed are methods for encoding information in a graphic image. The information may be encoded so as to have a visual appearance that adopts a particular style, so that the encoded information is visually pleasing in the environment in which it is displayed. An encoder and decoder are trained during an integrated training process, where the encoder is tuned to minimize a loss when its encoded images are decoded. Similarly, the decoder is also trained to minimize loss when decoding the encoded images. Both the encoder and decoder may utilize a convolutional neural network in some aspects to analyze data and/or images. Once data is encoded, a style from a sample image is transferred to the encoded data. When decoding, the decoder may largely ignore the style aspects of the encoded data and decode based on a content portion of the data.
-
公开(公告)号:US11887344B2
公开(公告)日:2024-01-30
申请号:US18128128
申请日:2023-03-29
Applicant: Snap Inc.
Inventor: Drake Austin Rehfeld , Rahul Bhupendra Sheth , Ning Zhang
Abstract: Disclosed are methods for encoding information in a graphic image. The information may be encoded so as to have a visual appearance that adopts a particular style, so that the encoded information is visually pleasing in the environment in which it is displayed. An encoder and decoder are trained during an integrated training process, where the encoder is tuned to minimize a loss when its encoded images are decoded. Similarly, the decoder is also trained to minimize loss when decoding the encoded images. Both the encoder and decoder may utilize a convolutional neural network in some aspects to analyze data and/or images. Once data is encoded, a style from a sample image is transferred to the encoded data. When decoding, the decoder may largely ignore the style aspects of the encoded data and decode based on a content portion of the data.
-
公开(公告)号:US11670012B2
公开(公告)日:2023-06-06
申请号:US17302361
申请日:2021-04-30
Applicant: Snap Inc.
Inventor: Drake Austin Rehfeld , Rahul Bhupendra Sheth , Ning Zhang
Abstract: Disclosed are methods for encoding information in a graphic image. The information may be encoded so as to have a visual appearance that adopts a particular style, so that the encoded information is visually pleasing in the environment in which it is displayed. An encoder and decoder are trained during an integrated training process, where the encoder is tuned to minimize a loss when its encoded images are decoded. Similarly, the decoder is also trained to minimize loss when decoding the encoded images. Both the encoder and decoder may utilize a convolutional neural network in some aspects to analyze data and/or images. Once data is encoded, a style from a sample image is transferred to the encoded data. When decoding, the decoder may largely ignore the style aspects of the encoded data and decode based on a content portion of the data.
-
公开(公告)号:US11527267B2
公开(公告)日:2022-12-13
申请号:US17303817
申请日:2021-06-08
Applicant: Snap Inc.
Inventor: Jia Li , Nathan Litke , Jose Jesus (Joseph) Paredes , Rahul Bhupendra Sheth , Daniel Szeto , Ning Xu , Jianchao Yang
IPC: H04N21/218 , H04N21/2343 , H04N21/431 , H04N21/44 , H04N21/4402 , H04N21/4728 , H04N21/63 , G11B27/10 , G11B27/031
Abstract: Systems and methods are described for determining a first media item related to an event, of a plurality of stored media items each comprising video content related to the event, that was captured in a device orientation corresponding to a first device orientation detected for the first computing device; providing, to the first computing device, the first media item to be displayed on the first computing device; in response to a detected change to a second device orientation for the first computing device, determining a second media item that was captured in a device orientation corresponding to the second device orientation detected for the first computing device; and providing, to the first computing device, the second media item to be displayed on the first computing device.
-
公开(公告)号:US10657676B1
公开(公告)日:2020-05-19
申请号:US16022536
申请日:2018-06-28
Applicant: Snap Inc.
Inventor: Drake Austin Rehfeld , Rahul Bhupendra Sheth , Ning Zhang
Abstract: Disclosed are methods for encoding information in a graphic image. The information may be encoded so as to have a visual appearance that adopts a particular style, so that the encoded information is visually pleasing in the environment in which it is displayed. An encoder and decoder are trained during an integrated training process, where the encoder is tuned to minimize a loss when its encoded images are decoded. Similarly, the decoder is also trained to minimize loss when decoding the encoded images. Both the encoder and decoder may utilize a convolutional neural network in some aspects to analyze data and/or images. Once data is encoded, a style from a sample image is transferred to the encoded data. When decoding, the decoder may largely ignore the style aspects of the encoded data and decode based on a content portion of the data.
-
公开(公告)号:US20200152238A1
公开(公告)日:2020-05-14
申请号:US16743563
申请日:2020-01-15
Applicant: Snap Inc.
Inventor: Jia Li , Nathan Litke , Jose Jesus (Joseph) Paredes , Rahul Bhupendra Sheth , Daniel Szeto , Ning Xu , Jianchao Yang
IPC: G11B27/10 , G11B27/031
Abstract: Systems and methods are described for determining a first media item related to an event, of a plurality of stored media items each comprising video content related to the event, that was captured in a device orientation corresponding to a first device orientation detected for the first computing device; providing, to the first computing device, the first media item to be displayed on the first computing device; in response to a detected change to a second device orientation for the first computing device, determining a second media item that was captured in a device orientation corresponding to the second device orientation detected for the first computing device; and providing, to the first computing device, the second media item to be displayed on the first computing device.
-
公开(公告)号:US10380394B1
公开(公告)日:2019-08-13
申请号:US15893165
申请日:2018-02-09
Applicant: Snap Inc.
Inventor: Nathan Kenneth Boyd , Christopher Jonathan Luc , Kirk Ouimet , Rahul Bhupendra Sheth
Abstract: Systems and methods for presenting an augmented reality within a custom graphic are provided. In example embodiments, one or more hardware processors may receive an image, identify candidate shape features in the image, identify a custom graphic by comparing the candidate shape features with a reference shape feature of the custom graphic, identify an optical barcode based on the identified custom graphic, identify an augmented reality based on the optical barcode, and transmit the augmented reality to the client device.
-
公开(公告)号:US20180089904A1
公开(公告)日:2018-03-29
申请号:US15830965
申请日:2017-12-04
Applicant: Snap Inc.
Inventor: Nathan Jurgenson , Linjie Luo , Jonathan M. Rodriguez, II , Rahul Bhupendra Sheth , Jia Li , Xutao Lv
IPC: G06T19/00 , G06T7/20 , G06T13/80 , G06F3/0481 , G06T19/20 , G06T7/73 , G06F3/01 , G06K9/00 , G06K9/78 , G06T7/246
CPC classification number: G06T19/006 , G06F3/012 , G06F3/04815 , G06K9/00624 , G06K9/00664 , G06K9/00671 , G06K9/78 , G06K2209/21 , G06T7/20 , G06T7/246 , G06T7/73 , G06T13/80 , G06T19/20 , G06T2200/04 , G06T2207/30244 , G06T2219/2004
Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.
-
公开(公告)号:US09922226B1
公开(公告)日:2018-03-20
申请号:US15262942
申请日:2016-09-12
Applicant: SNAP INC.
Inventor: Nathan Kenneth Boyd , Christopher Jonathan Luc , Kirk Ouimet , Rahul Bhupendra Sheth
IPC: G06K7/10 , G06K7/14 , G06K19/06 , G06F17/30 , G06F3/0484 , G06T11/60 , H04L29/06 , H04L29/08 , H04L12/58
CPC classification number: G06K7/1456 , G06F3/04842 , G06F17/30268 , G06F17/30879 , G06K7/1417 , G06K7/1443 , G06K7/1447 , G06K19/06037 , G06K19/06103 , G06K19/06112 , G06T11/60 , H04L51/04 , H04L51/32 , H04L67/306 , H04W4/80
Abstract: Systems and methods for presenting an augmented reality within a custom graphic are provided. In example embodiments, a server receives a scanned image from a client device, the scanned image including a custom graphic and an optical barcode. The server identifies an augmented reality and a user interface item based on the optical barcode. The server transmits the augmented reality to the client device for display, at the client device, within a custom graphic of the scanned image. The server receives an indication that the scanned image was selected at the client device. The server transmits, to the client device, the user interface item for display at the client device.
-
公开(公告)号:US12070682B2
公开(公告)日:2024-08-27
申请号:US16824373
申请日:2020-03-19
Applicant: Snap Inc.
Inventor: Dorian Franklin Baldwin , Jacob Edward Blackstock , Maoning Guo , David James Kennedy , Shahan Panth , Rahul Bhupendra Sheth , Leah Spontaneo , Wenzhou Wang , Artem Yagodin
Abstract: Systems and methods are disclosed for receiving a request to display an avatar within a graphical user interface of a client device, authenticating the request based on user data, retrieving the avatar from a database, transmitting the avatar to the client device and presenting the avatar within the user interface of the client device.
-
-
-
-
-
-
-
-
-