Patents by Inventor Tommer Leyvand
Tommer Leyvand 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: 10986384Abstract: A video application executing on a client device allows a user to modify video data captured by the client device. The video application allows the user to transmit the video data to a viewing client device for presentation to a viewing user. For example, the video application transmits the video data to an online system, which transmits the video data to the viewing client device. The viewing user provides a request to modify the video data to the viewing client device, which transmits the request to the online system. Based on the request from the viewing client device, the online system identifies a modification to the video data to the client device, which modifies the captured video data accordingly. The modified video data is provided from the client device to the viewing client device via the online system.Type: GrantFiled: December 26, 2017Date of Patent: April 20, 2021Assignee: Facebook, Inc.Inventors: Ragavan Srinivasan, Bryce David Redd, John Samuel Barnett, Tommer Leyvand
-
Patent number: 10152768Abstract: An image processing system transforms content images into the style of another reference style image. For example, the system applies a noise mask to generate noisy versions of the content images. The system then recomposes a content image in the style of a reference image by applying computer models to the noisy version of the content image, which reduces artifacts in the stylized image compared to that of a stylized image generated by applying the computer models to the original content image. When the content images are part of a video sequence, the image processing system may adjust the noise mask applied in a subsequent frame such that it tracks the movement of the client device from the current frame to the subsequent frame. This allows the system to reduce artifacts while stylizing the frames of the video in a consistent manner.Type: GrantFiled: April 14, 2017Date of Patent: December 11, 2018Assignee: Facebook, Inc.Inventors: Justin Johnson, Peter Vajda, Yangqing Jia, Tommer Leyvand
-
Patent number: 10147194Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may then be discarded to isolate one or more voxels associated with a foreground object such as a human target and the isolated voxels associated with the foreground object may be processed.Type: GrantFiled: May 8, 2017Date of Patent: December 4, 2018Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Craig Peeper, Johnny Lee, Tommer Leyvand, Szymon Stachniak
-
Publication number: 20180302659Abstract: A video application executing on a client device allows a user to modify video data captured by the client device. The video application allows the user to transmit the video data to a viewing client device for presentation to a viewing user. For example, the video application transmits the video data to an online system, which transmits the video data to the viewing client device. The viewing user provides a request to modify the video data to the viewing client device, which transmits the request to the online system. Based on the request from the viewing client device, the online system identifies a modification to the video data to the client device, which modifies the captured video data accordingly. The modified video data is provided from the client device to the viewing client device via the online system.Type: ApplicationFiled: December 26, 2017Publication date: October 18, 2018Inventors: Ragavan Srinivasan, Bryce David Redd, John Samuel Barnett, Tommer Leyvand
-
Publication number: 20180300850Abstract: An image processing system transforms content images into the style of another reference style image. For example, the system applies a noise mask to generate noisy versions of the content images. The system then recomposes a content image in the style of a reference image by applying computer models to the noisy version of the content image, which reduces artifacts in the stylized image compared to that of a stylized image generated by applying the computer models to the original content image. When the content images are part of a video sequence, the image processing system may adjust the noise mask applied in a subsequent frame such that it tracks the movement of the client device from the current frame to the subsequent frame. This allows the system to reduce artifacts while stylizing the frames of the video in a consistent manner.Type: ApplicationFiled: April 14, 2017Publication date: October 18, 2018Inventors: Justin Johnson, Peter Vajda, Yangqing Jia, Tommer Leyvand
-
Patent number: 10048747Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may also be removed to isolate one or more voxels associated with a foreground object such as a human target. A location or position of one or more extremities of the isolated human target may then be determined.Type: GrantFiled: April 21, 2017Date of Patent: August 14, 2018Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Johnny Chung Lee, Tommer Leyvand, Szymon Piotr Stachniak, Craig Peeper, Shao Liu
-
Patent number: 9821226Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may also be removed to isolate one or more voxels associated with a foreground object such as a human target. A location or position of one or more extremities of the isolated human target may be determined and a model may be adjusted based on the location or position of the one or more extremities.Type: GrantFiled: January 22, 2015Date of Patent: November 21, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Tommer Leyvand, Johnny Lee, Craig Peeper, Szymon Stachniak, Shao Liu
-
Patent number: 9823764Abstract: A method to identify a targeted object based on eye tracking and gesture recognition. The method is enacted in a compute system controlled by a user and operatively coupled to a machine vision system. In this method, the compute system receives, from the machine vision system, video imaging a head and pointer of the user. Based on the video, the compute system computes a geometric line of sight of the user, which is partly occluded by the pointer. Then, with reference to position data for one or more objects, the compute system identifies the targeted object, situated along the geometric line of sight.Type: GrantFiled: December 3, 2014Date of Patent: November 21, 2017Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Mark Schwesinger, Tommer Leyvand, Szymon Stachniak
-
Patent number: 9813600Abstract: Techniques for automatically selecting from amongst multiple camera views available in a multi-camera system. In an aspect, one or more metrics are calculated for multiple camera views. The metrics may be used to identify one or more of the camera views as fulfilling a condition, in response to which a particular one of the camera views may be selected for display. For example, in a “select-better-view” strategy, the camera view associated with a more optimal image (e.g., better lighting, or absence of occlusion) is selected for display. In a “flag-diagnostic-view” strategy, the camera view associated with a less optimal image is displayed, e.g., to indicate that a particular camera may require user attention. Specific techniques for calculating metrics are further disclosed.Type: GrantFiled: April 8, 2014Date of Patent: November 7, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Emad Barsoum, Tommer Leyvand, Spencer Perreault, Robert Smith, Michael Hall
-
Publication number: 20170287139Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may also be removed to isolate one or more voxels associated with a foreground object such as a human target. A location or position of one or more extremities of the isolated human target may then be determined.Type: ApplicationFiled: April 21, 2017Publication date: October 5, 2017Inventors: Johnny Chung Lee, Tommer Leyvand, Szymon Piotr Stachniak, Craig Peeper, Shao Liu
-
Publication number: 20170278251Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may then be discarded to isolate one or more voxels associated with a foreground object such as a human target and the isolated voxels associated with the foreground object may be processed.Type: ApplicationFiled: May 8, 2017Publication date: September 28, 2017Inventors: Craig Peeper, Johnny Lee, Tommer Leyvand, Szymon Stachniak
-
Patent number: 9703940Abstract: A computing system such as a game console maintains and updates a biometric profile of a user. In one aspect, biometric data of the user is continuously obtained from a sensor such as an infrared and visible light camera, and used to update the biometric profile using a machine learning process. In another aspect, a user is prompted to confirm his or her identify when multiple users are detected at the same time and/or when the user is detected with a confidence level which is below a threshold. A real-time image of the user being identified can be displayed on a user interface with user images associated with one or more accounts. In another aspect, the biometric profile is managed by a shell on the computing system, where the shell makes the biometric profile available to any of a number of applications on the computing system.Type: GrantFiled: December 23, 2014Date of Patent: July 11, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Ronald Forbes, Bhaven Dedhia, Tim Keosababian, Tommer Leyvand, Jinyu Li, Timothy Gerken
-
Patent number: 9679390Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may then be discarded to isolate one or more voxels associated with a foreground object such as a human target and the isolated voxels associated with the foreground object may be processed.Type: GrantFiled: December 30, 2013Date of Patent: June 13, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Craig Peeper, Johnny Lee, Tommer Leyvand, Szymon Stachniak
-
Patent number: 9659377Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may also be removed to isolate one or more voxels associated with a foreground object such as a human target. A location or position of one or more extremities of the isolated human target may then be determined.Type: GrantFiled: December 15, 2014Date of Patent: May 23, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Johnny Chung Lee, Tommer Leyvand, Szymon Piotr Stachniak, Craig Peeper, Shao Liu
-
Patent number: 9582717Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A model may be adjusted based on a location or position of one or more extremities estimated or determined for a human target in the grid of voxels. The model may also be adjusted based on a default location or position of the model in a default pose such as a T-pose, a DaVinci pose, and/or a natural pose.Type: GrantFiled: October 27, 2014Date of Patent: February 28, 2017Assignee: Microsoft Technology Licensing, LLCInventors: Johnny Chung Lee, Tommer Leyvand, Szymon Piotr Stachniak, Craig C. Peeper
-
Patent number: 9571816Abstract: A method comprises receiving one or more depth images from a depth camera, the depth images indicating a depth of a surface imaged by each pixel of the depth images. The method may further comprise identifying a human subject imaged by the depth images and recognizing within one or more of the depth images a beacon emitted from a control device. A position of the control device may be assessed in three dimensions, and the control device may be associated with the human subject based on a proximity of the control device to the human subject or other parameter of the control device with relation to the human subject.Type: GrantFiled: November 16, 2012Date of Patent: February 14, 2017Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Vijay Baiyya, Tommer Leyvand, Mark Plagge, Dawson Yee, John Link, Bryon Ashley, Andrew Jesse Milluzzi
-
Patent number: 9539500Abstract: A method for biometric identification for use with a computing device is provided herein. The method includes capturing a temporal sequence of images of the face of a user at different locations within a three-dimensional interaction space. The method further includes extracting one or more face descriptors from the images and generating a biometric template compiling the face descriptors.Type: GrantFiled: August 5, 2014Date of Patent: January 10, 2017Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Tommer Leyvand, Jinyu Li, Casey Meekhof, Tim Keosababian, Simon Stachniak, Ryan Gunn, Alan Stuart, Russ Glaser, Eddie Mays, Toan Huynh, Richard Irving, James Waletzky, Ajay Ramjee
-
Patent number: 9522328Abstract: An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may also be removed to isolate one or more voxels associated with a foreground object such as a human target. A location or position of one or more extremities of the isolated human target may be determined and a model may be adjusted based on the location or position of the one or more extremities.Type: GrantFiled: September 4, 2014Date of Patent: December 20, 2016Assignee: Microsoft Technology Licensing, LLCInventors: Tommer Leyvand, Johnny Chung Lee, Szymon Stachniak, Craig Peeper, Shao Liu
-
Patent number: 9524554Abstract: A control device includes a housing. The control device also includes a wireless communicator interior the housing. The wireless communicator wirelessly sends commands for controlling an electronic device, such as a game console. The control device also includes a reflector positioned to reflect light directed at the housing.Type: GrantFiled: December 21, 2015Date of Patent: December 20, 2016Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Mark Plagge, Vijay Baiyya, Tommer Leyvand, Susan Shuchen Song
-
Patent number: 9465980Abstract: A method of tracking a subject includes receiving from a source a depth image of a scene including the subject. The depth image includes a depth for each of a plurality of pixels. The method further includes identifying pixels of the depth image that image the subject and deriving from the identified pixels of the depth image one or more machine readable data structures representing the subject as a model including a plurality of shapes.Type: GrantFiled: September 5, 2014Date of Patent: October 11, 2016Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Robert Matthew Craig, Tommer Leyvand, Craig Peeper, Momin M. Al-Ghosien, Matt Bronder, Oliver Williams, Ryan M. Geiss, Jamie Daniel Joseph Shotton, Johnny Lee, Mark Finocchio