Patents by Inventor Sergei Kotcur
Sergei Kotcur 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: 20230384918Abstract: A system of machine learning schemes can be configured to efficiently perform image processing tasks on a user device, such as a mobile phone. The system can selectively detect and transform individual regions within each frame of a live streaming video. The system can selectively partition and toggle image effects within the live streaming video.Type: ApplicationFiled: August 9, 2023Publication date: November 30, 2023Inventors: Theresa Barton, Yanping Chen, Jaewook Chung, Christopher Crutchfield, Aymeric Damien, Sergei Kotcur, Igor Kudriashov, Sergey Tulyakov, Andrew Wan, Emre Yamangil
-
Publication number: 20230334327Abstract: A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.Type: ApplicationFiled: June 22, 2023Publication date: October 19, 2023Inventors: Sergey Tulyakov, Sergei Korolev, Aleksei Stoliar, Maksim Gusarov, Sergei Kotcur, Christopher Yale Crutchfield, Andrew Wan
-
Patent number: 11775158Abstract: A system of machine learning schemes can be configured to efficiently perform image processing tasks on a user device, such as a mobile phone. The system can selectively detect and transform individual regions within each frame of a live streaming video. The system can selectively partition and toggle image effects within the live streaming video.Type: GrantFiled: June 22, 2021Date of Patent: October 3, 2023Assignee: Snap Inc.Inventors: Theresa Barton, Yanping Chen, Jaewook Chung, Christopher Yale Crutchfield, Aymeric Damien, Sergei Kotcur, Igor Kudriashov, Sergey Tulyakov, Andrew Wan, Emre Yamangil
-
Patent number: 11727280Abstract: A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.Type: GrantFiled: March 2, 2021Date of Patent: August 15, 2023Assignee: Snap Inc.Inventors: Sergey Tulyakov, Sergei Korolev, Aleksei Stoliar, Maksim Gusarov, Sergei Kotcur, Christopher Yale Crutchfield, Andrew Wan
-
Patent number: 11676412Abstract: Systems, devices, and methods are presented for segmenting an image of a video stream with a client device by receiving one or more images depicting an object of interest and determining pixels within the one or more images corresponding to the object of interest. The systems, devices, and methods identify a position of a portion of the object of interest and determine a direction for the portion of the object of interest. Based on the direction of the portion of the object of interest, a histogram threshold is dynamically modified for identifying pixels as corresponding to the portion of the object of interest. The portion of the object of interest is replaced with a graphical interface element aligned with the direction of the portion of the object of interest.Type: GrantFiled: September 16, 2020Date of Patent: June 13, 2023Assignee: Snap Inc.Inventors: Victor Shaburov, Yurii Monastyrshyn, Oleksandr Pyshchenko, Sergei Kotcur
-
Patent number: 11631276Abstract: Systems, devices, media, and methods are presented for generating facial representations using image segmentation with a client device. The systems and methods receive an image depicting a face, detect at least a portion of the face within the image, and identify a set of facial landmarks within the portion of the face. The systems and methods determine one or more characteristics representing the portion of the face, in response to detecting the portion of the face. Based on the one or more characteristics and the set of facial landmarks, the systems and methods generate a representation of a face.Type: GrantFiled: June 9, 2021Date of Patent: April 18, 2023Assignee: Snap Inc.Inventors: Maksim Gusarov, Igor Kudriashov, Valerii Filev, Sergei Kotcur
-
Publication number: 20210311618Abstract: A system of machine learning schemes can be configured to efficiently perform image processing tasks on a user device, such as a mobile phone. The system can selectively detect and transform individual regions within each frame of a live streaming video. The system can selectively partition and toggle image effects within the live streaming video.Type: ApplicationFiled: June 22, 2021Publication date: October 7, 2021Inventors: Theresa Barton, Yanping Chen, Jaewook Chung, Christopher Yale Crutchfield, Aymeric Damien, Sergei Kotcur, Igor Kudriashov, Sergey Tulyakov, Andrew Wan, Emre Yamangil
-
Publication number: 20210295018Abstract: Systems, devices, media, and methods are presented for generating facial representations using image segmentation with a client device. The systems and methods receive an image depicting a face, detect at least a portion of the face within the image, and identify a set of facial landmarks within the portion of the face. The systems and methods determine one or more characteristics representing the portion of the face, in response to detecting the portion of the face. Based on the one or more characteristics and the set of facial landmarks, the systems and methods generate a representation of a face.Type: ApplicationFiled: June 9, 2021Publication date: September 23, 2021Inventors: Maksim Gusarov, Igor Kudriashov, Valerii Filev, Sergei Kotcur
-
Patent number: 11068141Abstract: A system of machine learning schemes can be configured to efficiently perform image processing tasks on a user device, such as a mobile phone. The system can selectively detect and transform individual regions within each frame of a live streaming video. The system can selectively partition and toggle image effects within the live streaming video.Type: GrantFiled: February 1, 2019Date of Patent: July 20, 2021Assignee: Snap Inc.Inventors: Theresa Barton, Yanping Chen, Jaewook Chung, Christopher Yale Crutchfield, Aymeric Damien, Sergei Kotcur, Igor Kudriashov, Sergey Tulyakov, Andrew Wan, Emre Yamangil
-
Patent number: 11048916Abstract: Systems, devices, media, and methods are presented for generating facial representations using image segmentation with a client device. The systems and methods receive an image depicting a face, detect at least a portion of the face within the image, and identify a set of facial landmarks within the portion of the face. The systems and methods determine one or more characteristics representing the portion of the face, in response to detecting the portion of the face. Based on the one or more characteristics and the set of facial landmarks, the systems and methods generate a representation of a face.Type: GrantFiled: May 10, 2019Date of Patent: June 29, 2021Assignee: Snap Inc.Inventors: Maksim Gusarov, Igor Kudriashov, Valerii Filev, Sergei Kotcur
-
Publication number: 20210182624Abstract: A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.Type: ApplicationFiled: March 2, 2021Publication date: June 17, 2021Inventors: Sergey Tulyakov, Sergei Korolev, Aleksei Stoliar, Maksim Gusarov, Sergei Kotcur, Christopher Yale Crutchfield, Andrew Wan
-
Patent number: 10963748Abstract: A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.Type: GrantFiled: August 31, 2018Date of Patent: March 30, 2021Assignee: Snap Inc.Inventors: Sergey Tulyakov, Sergei Korolev, Aleksei Stoliar, Maksim Gusarov, Sergei Kotcur, Christopher Yale Crutchfield, Andrew Wan
-
Publication number: 20200410227Abstract: Systems, devices, and methods are presented for segmenting an image of a video stream with a client device by receiving one or more images depicting an object of interest and determining pixels within the one or more images corresponding to the object of interest. The systems, devices, and methods identify a position of a portion of the object of interest and determine a direction for the portion of the object of interest. Based on the direction of the portion of the object of interest, a histogram threshold is dynamically modified for identifying pixels as corresponding to the portion of the object of interest. The portion of the object of interest is replaced with a graphical interface element aligned with the direction of the portion of the object of interest.Type: ApplicationFiled: September 16, 2020Publication date: December 31, 2020Inventors: Victor Shaburov, Yurii Monastyrshyn, Oleksandr Pyshchenko, Sergei Kotcur
-
Patent number: 10810418Abstract: Systems, devices, and methods are presented for segmenting an image of a video stream with a client device by receiving one or more images depicting an object of interest and determining pixels within the one or more images corresponding to the object of interest. The systems, devices, and methods identify a position of a portion of the object of interest and determine a direction for the portion of the object of interest. Based on the direction of the portion of the object of interest, a histogram threshold is dynamically modified for identifying pixels as corresponding to the portion of the object of interest. The portion of the object of interest is replaced with a graphical interface element aligned with the direction of the portion of the object of interest.Type: GrantFiled: September 5, 2018Date of Patent: October 20, 2020Assignee: Snap Inc.Inventors: Victor Shaburov, Yurii Monastyrshyn, Oleksandr Pyshchenko, Sergei Kotcur
-
Publication number: 20190266390Abstract: Systems, devices, media, and methods are presented for generating facial representations using image segmentation with a client device. The systems and methods receive an image depicting a face, detect at least a portion of the face within the image, and identify a set of facial landmarks within the portion of the face. The systems and methods determine one or more characteristics representing the portion of the face, in response to detecting the portion of the face. Based on the one or more characteristics and the set of facial landmarks, the systems and methods generate a representation of a face.Type: ApplicationFiled: May 10, 2019Publication date: August 29, 2019Inventors: Maksim Gusarov, Igor Kudriashov, Valerii Filev, Sergei Kotcur
-
Patent number: 10339365Abstract: Systems, devices, media, and methods are presented for generating facial representations using image segmentation with a client device. The systems and methods receive an image depicting a face, detect at least a portion of the face within the image, and identify a set of facial landmarks within the portion of the face. The systems and methods determine one or more characteristics representing the portion of the face, in response to detecting the portion of the face. Based on the one or more characteristics and the set of facial landmarks, the systems and methods generate a representation of a face.Type: GrantFiled: March 31, 2016Date of Patent: July 2, 2019Assignee: Snap Inc.Inventors: Maksim Gusarov, Igor Kudriashov, Valerii Filev, Sergei Kotcur
-
Patent number: 10102423Abstract: Systems, devices, and methods are presented for segmenting an image of a video stream with a client device by receiving one or more images depicting an object of interest and determining pixels within the one or more images corresponding to the object of interest. The systems, devices, and methods identify a position of a portion of the object of interest and determine a direction for the portion of the object of interest. Based on the direction of the portion of the object of interest, a histogram threshold is dynamically modified for identifying pixels as corresponding to the portion of the object of interest. The portion of the object of interest is replaced with a graphical interface element aligned with the direction of the portion of the object of interest.Type: GrantFiled: June 30, 2016Date of Patent: October 16, 2018Assignee: Snap Inc.Inventors: Victor Shaburov, Yurii Monastyrshyn, Oleksandr Pyshchenko, Sergei Kotcur
-
Publication number: 20170286752Abstract: Systems, devices, media, and methods are presented for generating facial representations using image segmentation with a client device. The systems and methods receive an image depicting a face, detect at least a portion of the face within the image, and identify a set of facial landmarks within the portion of the face. The systems and methods determine one or more characteristics representing the portion of the face, in response to detecting the portion of the face. Based on the one or more characteristics and the set of facial landmarks, the systems and methods generate a representation of a face.Type: ApplicationFiled: March 31, 2016Publication date: October 5, 2017Inventors: Maksim Gusarov, Igor Kudriashov, Valerii Filev, Sergei Kotcur