Patents by Inventor Houman Meshkin
Houman Meshkin 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).
-
Patent number: 11871139Abstract: Methods, systems, and storage media for simultaneously recording multiple visual media using a plurality of cameras of a visual media recording device are disclosed. Exemplary implementations may: record a first visual medium using a first camera (e.g., a front-facing camera) of the plurality of cameras of the visual media recording device; record a second visual medium using a second camera (e.g., a rear-facing camera) of the plurality of cameras of the visual media recording device simultaneously with recording of the first visual medium, at least one of the first camera and the second camera utilizing face-tracking technology during recording; combine the first visual medium and the second visual medium into a single visual output during a post-recording process; and cause display of the single visual output.Type: GrantFiled: July 23, 2021Date of Patent: January 9, 2024Assignee: Meta Platforms, Inc.Inventors: Doheny Yoon, Brandon Joseph Kieft, Raj Vir, George Lewis Kedenburg, III, Nicolas Russell, Bruno Pereira Evangelista, George Lam, Alexandra Louise Krakaris, Mitchell Kogan, Nilesh Vinubhai Patel, Houman Meshkin, Arielle Chapin
-
Patent number: 11765335Abstract: Systems, methods, and computing devices for capturing synthetic stereoscopic content are provided. An example computing device includes at least one processor and memory. The memory stores instructions that cause the computing device to receive a three-dimensional scene. The instructions may additionally cause the computing device to reposition vertices of the three-dimensional scene to compensate for variations in camera location in a directional stereoscopic projection and generate a stereoscopic image based on the repositioned vertices. An example method includes projecting a three-dimensional scene onto a left eye image cube and a right eye image cube and repositioning vertices of the three-dimensional scene to adjust for rendering from a single camera location. The method also includes mapping pixels of a stereoscopic image to points on the left eye image cube and the right eye image cube and generating the stereoscopic image using the values of the mapped pixels.Type: GrantFiled: October 4, 2021Date of Patent: September 19, 2023Assignee: Google LLCInventors: Jeremy Chernobieff, Houman Meshkin, Scott Dolim
-
Publication number: 20230146181Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for outputting filtered visual media content items. Various aspects may include receiving an input frame of a visual media content item. Aspects may also include training a machine learning algorithm based on a dataset of bracketed images. Aspects may include configuring a neural network based on image filtering of the input frame and via a shader component of a graphics processing unit. Aspects may include determining portions of the input frame that are associated with an extent of darkness. Aspects may include performing an image enhancement operation to the portions of the input frame. Aspects may include providing instructions to display an output frame changed by the image enhancement operation.Type: ApplicationFiled: November 8, 2021Publication date: May 11, 2023Inventors: Houman Meshkin, Jeong-Mo Hong
-
Publication number: 20220030213Abstract: Systems, methods, and computing devices for capturing synthetic stereoscopic content are provided. An example computing device includes at least one processor and memory. The memory stores instructions that cause the computing device to receive a three-dimensional scene. The instructions may additionally cause the computing device to reposition vertices of the three-dimensional scene to compensate for variations in camera location in a directional stereoscopic projection and generate a stereoscopic image based on the repositioned vertices. An example method includes projecting a three-dimensional scene onto a left eye image cube and a right eye image cube and repositioning vertices of the three-dimensional scene to adjust for rendering from a single camera location. The method also includes mapping pixels of a stereoscopic image to points on the left eye image cube and the right eye image cube and generating the stereoscopic image using the values of the mapped pixels.Type: ApplicationFiled: October 4, 2021Publication date: January 27, 2022Inventors: Jeremy Chernobieff, Houman Meshkin, Scott Dolim
-
Patent number: 11182613Abstract: In one embodiment, a method includes a system accessing an image, which may comprise covered and uncovered portions, and an overlay image comprising opaque pixels. The covered portion may be configured to be covered by the opaque pixels of the overlay image. The system may generate a data structure comprising data elements associated with pixels of the image. Each of the data elements associated with a covered pixel in the covered portion of the image may be configured to identify an uncovered pixel in the uncovered portion of the image that is closest to the covered pixel. Each covered pixel in the covered portion of the image may be modified by accessing the data element associated with the covered pixel, determining a distance between the covered pixel and an associated closest uncovered pixel using the accessed data element, and modifying a color of the covered pixel based on the distance.Type: GrantFiled: June 9, 2017Date of Patent: November 23, 2021Assignee: Facebook, Inc.Inventors: William S. Bailey, Ficus Kirkpatrick, Houman Meshkin, Ryan Keenan Olson, Hermes Germi Pique Corchs
-
Patent number: 11178385Abstract: Systems, methods, and computing devices for capturing synthetic stereoscopic content are provided. An example computing device includes at least one processor and memory. The memory stores instructions that cause the computing device to receive a three-dimensional scene. The instructions may additionally cause the computing device to reposition vertices of the three-dimensional scene to compensate for variations in camera location in a directional stereoscopic projection and generate a stereoscopic image based on the repositioned vertices. An example method includes projecting a three-dimensional scene onto a left eye image cube and a right eye image cube and repositioning vertices of the three-dimensional scene to adjust for rendering from a single camera location. The method also includes mapping pixels of a stereoscopic image to points on the left eye image cube and the right eye image cube and generating the stereoscopic image using the values of the mapped pixels.Type: GrantFiled: March 25, 2020Date of Patent: November 16, 2021Assignee: Google LLCInventors: Jeremy Chernobieff, Houman Meshkin, Scott Dolim
-
Patent number: 11069094Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for rendering makeup products on a user's face within an augmented reality environment in real-time. For example, the disclosed system can use blend a base makeup color of a selected makeup product with extracted luminance frequencies of a video stream. The disclosed system can then convert the blended makeup color to LAB color space and apply one or more shader models to the lightness of the color based on a material of the selected makeup product. The disclosed system can also apply additional operations for smoothing the skin of the user and matching the makeup product to a skin tone of the user. The disclosed system can then display the makeup product and any additional changes in an augmented reality environment in the video stream.Type: GrantFiled: May 13, 2019Date of Patent: July 20, 2021Assignee: FACEBOOK, INC.Inventors: Bruno Pereira Evangelista, Houman Meshkin, Ben Max Rubinstein, Helen Haekwang Kim, Anaelisa Aburto, David Michael Garrison Hill, Chayan Goswami, Sung Kyu Robin Kim, Ian Heisters, Catherine Yoo, Ernest Rowe
-
Publication number: 20200228786Abstract: Systems, methods, and computing devices for capturing synthetic stereoscopic content are provided. An example computing device includes at least one processor and memory. The memory stores instructions that cause the computing device to receive a three-dimensional scene. The instructions may additionally cause the computing device to reposition vertices of the three-dimensional scene to compensate for variations in camera location in a directional stereoscopic projection and generate a stereoscopic image based on the repositioned vertices. An example method includes projecting a three-dimensional scene onto a left eye image cube and a right eye image cube and repositioning vertices of the three-dimensional scene to adjust for rendering from a single camera location. The method also includes mapping pixels of a stereoscopic image to points on the left eye image cube and the right eye image cube and generating the stereoscopic image using the values of the mapped pixels.Type: ApplicationFiled: March 25, 2020Publication date: July 16, 2020Inventors: Jeremy Chernobieff, Houman Meshkin, Scott Dolim
-
Patent number: 10645370Abstract: Systems, methods, and computing devices for capturing synthetic stereoscopic content are provided. An example computing device includes at least one processor and memory. The memory stores instructions that cause the computing device to receive a three-dimensional scene. The instructions may additionally cause the computing device to reposition vertices of the three-dimensional scene to compensate for variations in camera location in a directional stereoscopic projection and generate a stereoscopic image based on the repositioned vertices. An example method includes projecting a three-dimensional scene onto a left eye image cube and a right eye image cube and repositioning vertices of the three-dimensional scene to adjust for rendering from a single camera location. The method also includes mapping pixels of a stereoscopic image to points on the left eye image cube and the right eye image cube and generating the stereoscopic image using the values of the mapped pixels.Type: GrantFiled: April 27, 2018Date of Patent: May 5, 2020Assignee: GOOGLE LLCInventors: Jeremy Chernobieff, Houman Meshkin, Scott Dolim
-
Publication number: 20180357480Abstract: In one embodiment, a method includes a system accessing an image, which may comprise covered and uncovered portions, and an overlay image comprising opaque pixels. The covered portion may be configured to be covered by the opaque pixels of the overlay image. The system may generate a data structure comprising data elements associated with pixels of the image. Each of the data elements associated with a covered pixel in the covered portion of the image may be configured to identify an uncovered pixel in the uncovered portion of the image that is closest to the covered pixel. Each covered pixel in the covered portion of the image may be modified by accessing the data element associated with the covered pixel, determining a distance between the covered pixel and an associated closest uncovered pixel using the accessed data element, and modifying a color of the covered pixel based on the distance.Type: ApplicationFiled: June 9, 2017Publication date: December 13, 2018Inventors: William S. Bailey, Ficus Kirkpatrick, Houman Meshkin, Ryan Keenan Olson, Hermes Germi Pique Corchs
-
Publication number: 20180316908Abstract: Systems, methods, and computing devices for capturing synthetic stereoscopic content are provided. An example computing device includes at least one processor and memory. The memory stores instructions that cause the computing device to receive a three-dimensional scene. The instructions may additionally cause the computing device to reposition vertices of the three-dimensional scene to compensate for variations in camera location in a directional stereoscopic projection and generate a stereoscopic image based on the repositioned vertices. An example method includes projecting a three-dimensional scene onto a left eye image cube and a right eye image cube and repositioning vertices of the three-dimensional scene to adjust for rendering from a single camera location. The method also includes mapping pixels of a stereoscopic image to points on the left eye image cube and the right eye image cube and generating the stereoscopic image using the values of the mapped pixels.Type: ApplicationFiled: April 27, 2018Publication date: November 1, 2018Inventors: Jeremy Chernobieff, Houman Meshkin, Scott Dolim
-
Patent number: 7973676Abstract: A method for controlling the movement of vehicles including removing a portable transmitter assembly and a portable receiving assembly from a vehicle, disposing the portable receiving assembly contiguous to an area where at least one vehicle travels, and illuminating at least one indicator on the portable receiving assembly with the portable transmitter assembly for controlling the movement of vehicles. An assembly for controlling the movement of vehicles includes a computer-readable medium.Type: GrantFiled: June 6, 2007Date of Patent: July 5, 2011Inventors: Mohammad Meshkin, Houman Meshkin, John Wade Carpenter
-
Publication number: 20080303695Abstract: A method for controlling the movement of vehicles including removing a portable transmitter assembly and a portable receiving assembly from a vehicle, disposing the portable receiving assembly contiguous to an area where at least one vehicle travels, and illuminating at least one indicator on the portable receiving assembly with the portable transmitter assembly for controlling the movement of vehicles. An assembly for controlling the movement of vehicles includes a computer-readable medium.Type: ApplicationFiled: June 6, 2007Publication date: December 11, 2008Inventors: Mohammad Meshkin, Houman Meshkin