公开(公告)号：US20230237706A1

公开(公告)日：2023-07-27

申请号：US18128128

申请日：2023-03-29

Applicant: Snap Inc.

Inventor： Drake Austin Rehfeld ,  Rahul Bhupendra Sheth ,  Ning Zhang

IPC: G06T9/00 ,  H04L51/52 ,  G06N3/047

CPC classification number: G06T9/002 ,  H04L51/52 ,  G06N3/047

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：US20210256736A1

公开(公告)日：2021-08-19

申请号：US17302361

申请日：2021-04-30

Applicant: Snap Inc. Prefix

Inventor： Drake Austin Rehfeld ,  Rahul Bhupendra Sheth ,  Ning Zhang

IPC: G06T9/00 ,  H04L12/58 ,  G06N3/04

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：US20240054687A1

公开(公告)日：2024-02-15

申请号：US18382729

申请日：2023-10-23

Applicant: Snap Inc.

Inventor： Drake Austin Rehfeld ,  Rahul Bhupendra Sheth ,  Ning Zhang

IPC: G06T9/00 ,  H04L51/52 ,  G06N3/047

CPC classification number: G06T9/002 ,  H04L51/52 ,  G06N3/047

Abstract: An example system includes an encoder configured to receive a bit string and encode the bit string into a visual representation, and a decoder configured to receive an image including the visual representation and decode the bit string from the visual representation. In some examples, the encoder and decoder are trained as a pair by obtaining a training bit string, encoding the training bit string into a training visual representation using the encoder, decoding the training visual representation using the decoder to generate a decoded bit string, determining an error between the training bit string and the decoded bit string, and updating parameters of the encoder and decoder to reduce the error.

公开(公告)号：US11024058B2

公开(公告)日：2021-06-01

申请号：US16846949

申请日：2020-04-13

Applicant: Snap Inc.

Inventor： Drake Austin Rehfeld ,  Rahul Bhupendra Sheth ,  Ning Zhang

IPC: G06T9/00 ,  H04L12/58 ,  G06N3/04

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：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

IPC: G06T9/00 ,  H04L12/58 ,  G06N3/04

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

IPC: H04L51/52 ,  G06T9/00 ,  G06N3/047

CPC classification number: G06T9/002 ,  G06N3/047 ,  H04L51/52

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

IPC: G06T9/00 ,  H04L51/52 ,  G06N3/047

CPC classification number: G06T9/002 ,  G06N3/047 ,  H04L51/52

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：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

IPC: H04N19/00 ,  G06T9/00 ,  H04L12/58 ,  G06N3/04

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.