Patents by Inventor Xutao Lv
Xutao Lv 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: 11769307Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.Type: GrantFiled: April 25, 2022Date of Patent: September 26, 2023Assignee: Snap Inc.Inventors: Nathan Jurgenson, Linjie Luo, Jonathan M. Rodriguez, II, Rahul Bhupendra Sheth, Jia Li, Xutao Lv
-
Publication number: 20220406008Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. Point cloud data describing an environment is then accessed. A two-dimensional surface of an image of an environment is captured, and a portion of the image is matched to a portion of key points in the point cloud data. An augmented reality object is then aligned within one or more images of the environment based on the match of the point cloud with the image. In some embodiments, building façade data may additionally be used to determine a device location and place the augmented reality object within an image.Type: ApplicationFiled: July 1, 2022Publication date: December 22, 2022Inventors: Nathan Jurgenson, Linjie Luo, Jonathan M. Rodriguez, II, Rahul Bhupendra Sheth, Jia Li, Xutao Lv
-
Publication number: 20220245907Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.Type: ApplicationFiled: April 25, 2022Publication date: August 4, 2022Inventors: Nathan Jurgenson, Linjie Luo, Jonathan M. Rodriguez, II, Rahul Bhupendra Sheth, Jia Li, Xutao Lv
-
Patent number: 11380051Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. Point cloud data describing an environment is then accessed. A two-dimensional surface of an image of an environment is captured, and a portion of the image is matched to a portion of key points in the point cloud data. An augmented reality object is then aligned within one or more images of the environment based on the match of the point cloud with the image. In some embodiments, building façade data may additionally be used to determine a device location and place the augmented reality object within an image.Type: GrantFiled: February 10, 2021Date of Patent: July 5, 2022Assignee: Snap Inc.Inventors: Nathan Jurgenson, Linjie Luo, Jonathan M Rodriguez, II, Rahul Sheth, Jia Li, Xutao Lv
-
Patent number: 11341177Abstract: An image captioning system and method is provided for generating a caption for an image. The image captioning system utilizes a policy network and a value network to generate the caption. The policy network serves as a local guidance and the value network serves as a global and lookahead guidance.Type: GrantFiled: December 20, 2019Date of Patent: May 24, 2022Assignee: Snap Inc.Inventors: Zhou Ren, Xiaoyu Wang, Ning Zhang, Xutao Lv, Jia Li
-
Patent number: 11315331Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.Type: GrantFiled: June 26, 2020Date of Patent: April 26, 2022Assignee: Snap Inc.Inventors: Nathan Jurgenson, Linjie Luo, Jonathan M Rodriguez, II, Rahul Sheth, Jia Li, Xutao Lv
-
Patent number: 11227221Abstract: Disclosed are a framework management method and an apparatus. The method includes: a server acquiring a training request sent by a client, wherein the training request includes a function command and configuration data including a type of model framework, a path of a script, a path of a training data set and model hyper-parameters; the server determining whether configurations of the server are correct; if so, the server acquiring a model framework mirror image corresponding to the type of the model framework; the server starting a container for operating the model framework mirror image; the server reading, according to the paths of the script and the training data set, the script and the training data set into the container for operation; and the server executing the function command to implement a function that the function command instructs the server to execute.Type: GrantFiled: October 31, 2019Date of Patent: January 18, 2022Assignee: SHENZHEN INTELLIFUSION TECHNOLOGIES CO., LTD.Inventors: Haigang Zheng, Xutao Lv, Xiaoyu Wang
-
Patent number: 11100311Abstract: Systems, devices, media, and methods are presented for modeling 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 features within the portion of the face. The systems and methods generate a descriptor function representing the set of facial features, fit object functions of the descriptor function, identify an identification probability for each facial feature, and assign an identification to each facial feature.Type: GrantFiled: July 11, 2019Date of Patent: August 24, 2021Assignee: Snap Inc.Inventors: Jia Li, Xutao Lv, Xiaoyu Wang, Xuehan Xiong, Jianchao Yang
-
Publication number: 20210248487Abstract: Disclosed are a framework management method and an apparatus. The method includes: a server acquiring a training request sent by a client, wherein the training request includes a function command and configuration data including a type of model framework, a path of a script, a path of a training data set and model hyper-parameters; the server determining whether configurations of the server are correct; if so, the server acquiring a model framework mirror image corresponding to the type of the model framework; the server starting a container for operating the model framework mirror image; the server reading, according to the paths of the script and the training data set, the script and the training data set into the container for operation; and the server executing the function command to implement a function that the function command instructs the server to execute.Type: ApplicationFiled: October 31, 2019Publication date: August 12, 2021Inventors: Haigang ZHENG, Xutao LV, Xiaoyu WANG
-
Patent number: 11074477Abstract: A computing system and method for identifying related visual content of a collection of visual media files comprising one or more image files and video files includes monitoring inputs to the computing system, the inputs associated with a user interaction with electronic content using the computer system, identifying a visual media file in the collection of visual media files relevant to the electronic content based on a semantic label assigned to the visual media file by the computing system, creating a representative image of the identified visual media file, and displaying the representative image for selection. The computing system enables a selection of the displayed representative image for association of the identified visual media file with the electronic content.Type: GrantFiled: July 20, 2017Date of Patent: July 27, 2021Assignee: SRI InternationalInventors: Harpreet Singh Sawhney, Jayakrishnan Eledath, Mayank Bansal, Bogdan C. Matei, Xutao Lv, Chaitanya Desai, Timothy Shields
-
Publication number: 20210174578Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. Point cloud data describing an environment is then accessed. A two-dimensional surface of an image of an environment is captured, and a portion of the image is matched to a portion of key points in the point cloud data. An augmented reality object is then aligned within one or more images of the environment based on the match of the point cloud with the image. In some embodiments, building façade data may additionally be used to determine a device location and place the augmented reality object within an image.Type: ApplicationFiled: February 10, 2021Publication date: June 10, 2021Inventors: Nathan Jurgenson, Linjie Luo, Jonathan M Rodriguez, II, Rahul Sheth, Jia Li, Xutao Lv
-
Patent number: 10997783Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. Point cloud data describing an environment is then accessed. A two-dimensional surface of an image of an environment is captured, and a portion of the image is matched to a portion of key points in the point cloud data. An augmented reality object is then aligned within one or more images of the environment based on the match of the point cloud with the image. In some embodiments, building façade data may additionally be used to determine a device location and place the augmented reality object within an image.Type: GrantFiled: March 19, 2020Date of Patent: May 4, 2021Assignee: Snap Inc.Inventors: Nathan Jurgenson, Linjie Luo, Jonathan M Rodriguez, II, Rahul Sheth, Jia Li, Xutao Lv
-
Publication number: 20200327738Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.Type: ApplicationFiled: June 26, 2020Publication date: October 15, 2020Inventors: Nathan Jurgenson, Linjie Luo, Jonathan M. Rodriguez, II, Rahul Sheth, Jia Li, Xutao Lv
-
Patent number: 10733802Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.Type: GrantFiled: June 11, 2019Date of Patent: August 4, 2020Assignee: Snap Inc.Inventors: Nathan Jurgenson, Linjie Luo, Jonathan M Rodriguez, II, Rahul Sheth, Jia Li, Xutao Lv
-
Patent number: 10726059Abstract: An image captioning system and method is provided for generating a caption for an image. The image captioning system utilizes a policy network and a value network to generate the caption. The policy network serves as a local guidance and the value network serves as a global and lookahead guidance.Type: GrantFiled: June 21, 2019Date of Patent: July 28, 2020Assignee: Snap Inc.Inventors: Zhou Ren, Xiaoyu Wang, Ning Zhang, Xutao Lv, Jia Li
-
Publication number: 20200219312Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. Point cloud data describing an environment is then accessed. A two-dimensional surface of an image of an environment is captured, and a portion of the image is matched to a portion of key points in the point cloud data. An augmented reality object is then aligned within one or more images of the environment based on the match of the point cloud with the image. In some embodiments, building façade data may additionally be used to determine a device location and place the augmented reality object within an image.Type: ApplicationFiled: March 19, 2020Publication date: July 9, 2020Inventors: Nathan Jurgenson, Linjie Luo, Jonathan M. Rodriguez, II, Rahul Sheth, Jia Li, Xutao Lv
-
Patent number: 10691743Abstract: A computing system for realizing visual content of an image collection executes feature detection algorithms and semantic reasoning techniques on the images in the collection to elicit a number of different types of visual features of the images. The computing system indexes the visual features and provides technologies for multi-dimensional content-based clustering, searching, and iterative exploration of the image collection using the visual features and/or the visual feature indices.Type: GrantFiled: August 5, 2014Date of Patent: June 23, 2020Assignee: SRI InternationalInventors: Harpreet Singh Sawhney, Jayakrishnan Eledath, Mayank Bansal, Bogdan C. Matei, Xutao Lv, Chaitanya Desai, Timothy Shields
-
Patent number: 10657708Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A 3D point cloud data describing an environment is then accessed. A first image of an environment is captured, and a portion of the image is matched to a portion of key points in the 3D point cloud data. An augmented reality object is then aligned within one or more images of the environment based on the match of the 3D point cloud with the image. In some embodiments, building façade data may additionally be used to determine a device location and place the augmented reality object within an image.Type: GrantFiled: May 4, 2018Date of Patent: May 19, 2020Assignee: Snap Inc.Inventors: Nathan Jurgenson, Linjie Luo, Jonathan M Rodriguez, II, Rahul Sheth, Jia Li, Xutao Lv
-
Patent number: 10467274Abstract: An image captioning system and method is provided for generating a caption for an image. The image captioning system utilizes a policy network and a value network to generate the caption. The policy network serves as a local guidance and the value network serves as a global and lookahead guidance.Type: GrantFiled: November 9, 2017Date of Patent: November 5, 2019Assignee: Snap Inc.Inventors: Zhou Ren, Xiaoyu Wang, Ning Zhang, Xutao Lv, Jia Li
-
Publication number: 20190332852Abstract: Systems, devices, media, and methods are presented for modeling 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 features within the portion of the face. The systems and methods generate a descriptor function representing the set of facial features, fit object functions of the descriptor function, identify an identification probability for each facial feature, and assign an identification to each facial feature.Type: ApplicationFiled: July 11, 2019Publication date: October 31, 2019Inventors: Jia Li, Xutao Lv, Xiaoyu Wang, Xuehan Xiong, Jiancho Yang