Patents by Inventor Drake Austin
Drake Austin has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240054687Abstract: 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.Type: ApplicationFiled: October 23, 2023Publication date: February 15, 2024Inventors: Drake Austin Rehfeld, Rahul Bhupendra Sheth, Ning Zhang
-
Patent number: 11887344Abstract: 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.Type: GrantFiled: March 29, 2023Date of Patent: January 30, 2024Assignee: Snap Inc.Inventors: Drake Austin Rehfeld, Rahul Bhupendra Sheth, Ning Zhang
-
Publication number: 20230237706Abstract: 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.Type: ApplicationFiled: March 29, 2023Publication date: July 27, 2023Inventors: Drake Austin Rehfeld, Rahul Bhupendra Sheth, Ning Zhang
-
Patent number: 11670012Abstract: 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.Type: GrantFiled: April 30, 2021Date of Patent: June 6, 2023Assignee: Snap Inc.Inventors: Drake Austin Rehfeld, Rahul Bhupendra Sheth, Ning Zhang
-
Publication number: 20210301381Abstract: The present invention relates to processes of making components for electronic and optical devices using laser processing and devices comprising such components. Such process uses a laser to introduce chemical and/or structural changes in substrates and films that are the raw materials from which components for electronic and optical devices are made. Such process yields components that can have one or more electronic and/or optical functionalities that are integrated on the same substrate or film. In addition, such process does not require large-scale clean rooms and is easily configurable. Thus, rapid device prototyping, design change and evolution in the lab and on the production side is realized.Type: ApplicationFiled: June 2, 2021Publication date: September 30, 2021Inventors: Nicholas R. Glavin, Philip R. Buskohl, Kimberly A. Gliebe, Christopher Muratore, Drake Austin
-
Publication number: 20210299781Abstract: The present invention relates to processes of making components for electronic and optical devices using laser processing and devices comprising such components. Such process uses a laser to introduce chemical and/or structural changes in substrates and films that are the raw materials from which components for electronic and optical devices are made. Such process yields components that can have one or more electronic and/or optical functionalities that are integrated on the same substrate or film. In addition, such process does not require large-scale clean rooms and is easily configurable. Thus, rapid device prototyping, design change and evolution in the lab and on the production side is realized.Type: ApplicationFiled: March 30, 2021Publication date: September 30, 2021Inventors: Nicholas R. Glavin, Philip R. Buskohl, Kimberly A. Gliebe, Christopher Muratore, Drake Austin
-
Publication number: 20210256736Abstract: 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.Type: ApplicationFiled: April 30, 2021Publication date: August 19, 2021Inventors: Drake Austin Rehfeld, Rahul Bhupendra Sheth, Ning Zhang
-
Patent number: 11024058Abstract: 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.Type: GrantFiled: April 13, 2020Date of Patent: June 1, 2021Assignee: Snap Inc.Inventors: Drake Austin Rehfeld, Rahul Bhupendra Sheth, Ning Zhang
-
Publication number: 20200242812Abstract: 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.Type: ApplicationFiled: April 13, 2020Publication date: July 30, 2020Inventors: Drake Austin Rehfeld, Rahul Bhupendra Sheth, Ning Zhang
-
Patent number: 10657676Abstract: 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.Type: GrantFiled: June 28, 2018Date of Patent: May 19, 2020Assignee: Snap Inc.Inventors: Drake Austin Rehfeld, Rahul Bhupendra Sheth, Ning Zhang