Patents by Inventor Zehao Xue
Zehao Xue 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: 11030454Abstract: A machine learning scheme can be trained on a set of labeled training images of a subject in different poses, with different textures, and with different background environments. The label or marker data of the subject may be stored as metadata to a 3D model of the subject or rendered images of the subject. The machine learning scheme may be implemented as a supervised learning scheme that can automatically identify the labeled data to create a classification model. The classification model can classify a depicted subject in many different environments and arrangements (e.g., poses).Type: GrantFiled: January 30, 2020Date of Patent: June 8, 2021Assignee: Snap Inc.Inventors: Xuehan Xiong, Zehao Xue
-
Patent number: 10997787Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and a method for receiving a monocular image that includes a depiction of a hand and extracting features of the monocular image using a plurality of machine learning techniques. The program and method further include modeling, based on the extracted features, a pose of the hand depicted in the monocular image by adjusting skeletal joint positions of a three-dimensional (3D) hand mesh using a trained graph convolutional neural network (CNN); modeling, based on the extracted features, a shape of the hand in the monocular image by adjusting blend shape values of the 3D hand mesh representing surface features of the hand depicted in the monocular image using the trained graph CNN; and generating, for display, the 3D hand mesh adjusted to model the pose and shape of the hand depicted in the monocular image.Type: GrantFiled: September 2, 2020Date of Patent: May 4, 2021Assignee: Snap Inc.Inventors: Liuhao Ge, Zhou Ren, Yuncheng Li, Zehao Xue, Yingying Wang
-
Publication number: 20210074016Abstract: Systems and methods herein describe using a neural network to identify a first set of joint location coordinates and a second set of joint location coordinates and identifying a three-dimensional hand pose based on both the first and second sets of joint location coordinates.Type: ApplicationFiled: September 9, 2020Publication date: March 11, 2021Inventors: Yuncheng Li, Jonathan M. Rodriguez, II, Zehao Xue, Yingying Wang
-
Publication number: 20210037179Abstract: A dolly zoom effect can be applied to one or more images captured via a resource-constrained device (e.g., a mobile smartphone) by manipulating the size of a target feature while the background in the one or more images changes due to physical movement of the resource-constrained device. The target feature can be detected using facial recognition or shape detection techniques. The target feature can be resized before the size is manipulated as the background changes (e.g., changes perspective).Type: ApplicationFiled: July 20, 2020Publication date: February 4, 2021Inventors: Linjie Luo, Chongyang Ma, Zehao Xue
-
Publication number: 20200402305Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and a method for receiving a monocular image that includes a depiction of a hand and extracting features of the monocular image using a plurality of machine learning techniques. The program and method further include modeling, based on the extracted features, a pose of the hand depicted in the monocular image by adjusting skeletal joint positions of a three-dimensional (3D) hand mesh using a trained graph convolutional neural network (CNN); modeling, based on the extracted features, a shape of the hand in the monocular image by adjusting blend shape values of the 3D hand mesh representing surface features of the hand depicted in the monocular image using the trained graph CNN; and generating, for display, the 3D hand mesh adjusted to model the pose and shape of the hand depicted in the monocular image.Type: ApplicationFiled: September 2, 2020Publication date: December 24, 2020Inventors: Liuhao Ge, Zhou Ren, Yuncheng Li, Zehao Xue, Yingying Wang
-
Patent number: 10796482Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and a method for receiving a monocular image that includes a depiction of a hand and extracting features of the monocular image using a plurality of machine learning techniques. The program and method further include modeling, based on the extracted features, a pose of the hand depicted in the monocular image by adjusting skeletal joint positions of a three-dimensional (3D) hand mesh using a trained graph convolutional neural network (CNN); modeling, based on the extracted features, a shape of the hand in the monocular image by adjusting blend shape values of the 3D hand mesh representing surface features of the hand depicted in the monocular image using the trained graph CNN; and generating, for display, the 3D hand mesh adjusted to model the pose and shape of the hand depicted in the monocular image.Type: GrantFiled: December 5, 2018Date of Patent: October 6, 2020Assignee: Snap Inc.Inventors: Liuhao Ge, Zhou Ren, Yuncheng Li, Zehao Xue, Yingying Wang
-
Patent number: 10757319Abstract: A dolly zoom effect can be applied to one or more images captured via a resource-constrained device (e.g., a mobile smartphone) by manipulating the size of a target feature while the background in the one or more images changes due to physical movement of the resource-constrained device. The target feature can be detected using facial recognition or shape detection techniques. The target feature can be resized before the size is manipulated as the background changes (e.g., changes perspective).Type: GrantFiled: June 15, 2017Date of Patent: August 25, 2020Assignee: Snap Inc.Inventors: Linjie Luo, Chongyang Ma, Zehao Xue
-
Publication number: 20200242826Abstract: Embodiments described herein relate to an augmented expression system to generate and cause display of a specially configured interface to present an augmented reality perspective. The augmented expression system receives image and video data of a user and tracks facial landmarks of the user based on the image and video data, in real-time to generate and present a 3-dimensional (3D) bitmoji of the user.Type: ApplicationFiled: April 15, 2020Publication date: July 30, 2020Inventors: Chen Cao, Yang Gao, Zehao Xue
-
Patent number: 10719968Abstract: Embodiments described herein relate to an augmented expression system to generate and cause display of a specially configured interface to present an augmented reality perspective. The augmented expression system receives image and video data of a user and tracks facial landmarks of the user based on the image and video data, in real-time to generate and present a 3-dimensional (3D) bitmoji of the user.Type: GrantFiled: April 17, 2019Date of Patent: July 21, 2020Assignee: Snap Inc.Inventors: Chen Cao, Yang Gao, Zehao Xue
-
Publication number: 20200184721Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and a method for receiving a monocular image that includes a depiction of a hand and extracting features of the monocular image using a plurality of machine learning techniques. The program and method further include modeling, based on the extracted features, a pose of the hand depicted in the monocular image by adjusting skeletal joint positions of a three-dimensional (3D) hand mesh using a trained graph convolutional neural network (CNN); modeling, based on the extracted features, a shape of the hand in the monocular image by adjusting blend shape values of the 3D hand mesh representing surface features of the hand depicted in the monocular image using the trained graph CNN; and generating, for display, the 3D hand mesh adjusted to model the pose and shape of the hand depicted in the monocular image.Type: ApplicationFiled: December 5, 2018Publication date: June 11, 2020Inventors: Liuhao Ge, Zhou Ren, Yuncheng Li, Zehao Xue, Yingying Wang
-
Publication number: 20200160580Abstract: The present invention relates to a joint automatic audio visual driven facial animation system that in some example embodiments includes a full scale state of the art Large Vocabulary Continuous Speech Recognition (LVCSR) with a strong language model for speech recognition and obtained phoneme alignment from the word lattice.Type: ApplicationFiled: January 22, 2020Publication date: May 21, 2020Inventors: Chen Cao, Xin Chen, Wei Chu, Zehao Xue
-
Patent number: 10643104Abstract: Systems and methods are provided for analyzing location data associated with a location of a computing device to determine that a media content item is captured near a food-related venue or event, presenting interactive features to capture input related to food associated with the food-related venue or event, receiving the input in response to the presented interactive features, sending the media content item and the input in response to the interactive features to a computing system to incorporate the media content item and input into a machine learning model for food detection, and updating a messaging application to update a food detector functionality of the messaging application to comprise an updated machine learning model for food detection based on the media content item and input in response to the interactive features.Type: GrantFiled: December 1, 2017Date of Patent: May 5, 2020Assignee: Snap Inc.Inventors: Zehao Xue, Zhou Ren
-
Patent number: 10586368Abstract: The present invention relates to a joint automatic audio visual driven facial animation system that in some example embodiments includes a full scale state of the art Large Vocabulary Continuous Speech Recognition (LVCSR) with a strong language model for speech recognition and obtained phoneme alignment from the word lattice.Type: GrantFiled: December 29, 2017Date of Patent: March 10, 2020Assignee: Snap Inc.Inventors: Chen Cao, Xin Chen, Wei Chu, Zehao Xue
-
Patent number: 10579869Abstract: A machine learning scheme can be trained on a set of labeled training images of a subject in different poses, with different textures, and with different background environments. The label or marker data of the subject may be stored as metadata to a 3D model of the subject or rendered images of the subject. The machine learning scheme may be implemented as a supervised learning scheme that can automatically identify the labeled data to create a classification model. The classification model can classify a depicted subject in many different environments and arrangements (e.g., poses).Type: GrantFiled: July 18, 2017Date of Patent: March 3, 2020Assignee: Snap Inc.Inventors: Xuehan Xiong, Zehao Xue
-
Publication number: 20190325631Abstract: The present invention relates to improvements to systems and methods for determining a current location of a client device, and for identifying and selecting appropriate geo-fences based on the current location of the client device. An improved geo-fence selection system performs operations that include associating media content with a geo-fence that encompasses a portion of a geographic region, sampling location data from a client device, defining a boundary based on the sampled location data from the client device, detecting an overlap between the boundary and the geo-fence, retrieving the media content associated with the geo-fence, and loading the media content at a memory location of the client device, in response to detecting the overlap.Type: ApplicationFiled: April 17, 2019Publication date: October 24, 2019Inventors: Chen Cao, Yang Gao, Zehao Xue
-
Publication number: 20190130628Abstract: The present invention relates to a joint automatic audio visual driven facial animation system that in some example embodiments includes a full scale state of the art Large Vocabulary Continuous Speech Recognition (LVCSR) with a strong language model for speech recognition and obtained phoneme alignment from the word lattice.Type: ApplicationFiled: December 29, 2017Publication date: May 2, 2019Inventors: Chen Cao, Xin Chen, Wei Chu, Zehao Xue