Patents by Inventor Xuehan Xiong
Xuehan Xiong 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: 20240046072Abstract: A modulated segmentation system can use a modulator network to emphasize spatial prior data of an object to track the object across multiple images. The modulated segmentation system can use a segmentation network that receives spatial prior data as intermediate data that improves segmentation accuracy. The segmentation network can further receive visual guide information from a visual guide network to increase tracking accuracy via segmentation.Type: ApplicationFiled: October 18, 2023Publication date: February 8, 2024Inventors: Linjie Yang, Jianchao Yang, Xuehan Xiong, Yanran Wang
-
Publication number: 20230419188Abstract: 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: ApplicationFiled: September 8, 2023Publication date: December 28, 2023Inventors: Xuehan Xiong, Zehao Xue
-
Publication number: 20230419538Abstract: A method includes receiving video data that includes a series of frames of image data. Here, the video data is representative of an actor performing an activity. The method also includes processing the video data to generate a spatial input stream including a series of spatial images representative of spatial features of the actor performing the activity, a temporal input stream representative of motion of the actor performing the activity, and a pose input stream including a series of images representative of a pose of the actor performing the activity. Using at least one neural network, the method also includes processing the temporal input stream, the spatial input stream, and the pose input stream. The method also includes classifying, by the at least one neural network, the activity based on the temporal input stream, the spatial input stream, and the pose input stream.Type: ApplicationFiled: September 11, 2023Publication date: December 28, 2023Applicant: Google LLCInventors: Yinxiao Li, Zhichao Lu, Xuehan Xiong, Jonathan Huang
-
Patent number: 11847528Abstract: A modulated segmentation system can use a modulator network to emphasize spatial prior data of an object to track the object across multiple images. The modulated segmentation system can use a segmentation network that receives spatial prior data as intermediate data that improves segmentation accuracy. The segmentation network can further receive visual guide information from a visual guide network to increase tracking accuracy via segmentation.Type: GrantFiled: December 29, 2022Date of Patent: December 19, 2023Assignee: Snap Inc.Inventors: Linjie Yang, Jianchao Yang, Xuehan Xiong, Yanran Wang
-
Publication number: 20230362331Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can be assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.Type: ApplicationFiled: July 13, 2023Publication date: November 9, 2023Inventors: Lidiia Bogdanovych, William Brendel, Samuel Edward Hare, Fedir Poliakov, Guohui Wang, Xuehan Xiong, Jianchao Yang, Linjie Yang
-
Patent number: 11790276Abstract: 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: May 17, 2021Date of Patent: October 17, 2023Assignee: Snap Inc.Inventors: Xuehan Xiong, Zehao Xue
-
Patent number: 11776156Abstract: A method includes receiving video data that includes a series of frames of image data. Here, the video data is representative of an actor performing an activity. The method also includes processing the video data to generate a spatial input stream including a series of spatial images representative of spatial features of the actor performing the activity, a temporal input stream representative of motion of the actor performing the activity, and a pose input stream including a series of images representative of a pose of the actor performing the activity. Using at least one neural network, the method also includes processing the temporal input stream, the spatial input stream, and the pose input stream. The method also includes classifying, by the at least one neural network, the activity based on the temporal input stream, the spatial input stream, and the pose input stream.Type: GrantFiled: June 11, 2021Date of Patent: October 3, 2023Assignee: Google LLCInventors: Yinxiao Li, Zhichao Lu, Xuehan Xiong, Jonathan Huang
-
Publication number: 20230274543Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.Type: ApplicationFiled: May 4, 2023Publication date: August 31, 2023Inventors: Samuel Edward Hare, Fedir Poliakov, Guohui Wang, Xuehan Xiong, Jianchao Yang, Linjie Yang, Shah Tanmay Anilkumar
-
Patent number: 11743426Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can he assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented. using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.Type: GrantFiled: August 13, 2020Date of Patent: August 29, 2023Assignee: Snap Inc.Inventors: Lidiia Bogdanovych, William Brendel, Samuel Edward Hare, Fedir Poliakov, Guohui Wang, Xuehan Xiong, Jianchao Yang, Linjie Yang
-
Patent number: 11676381Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.Type: GrantFiled: January 22, 2021Date of Patent: June 13, 2023Assignee: Snap Inc.Inventors: Samuel Edward Hare, Fedir Poliakov, Guohui Wang, Xuehan Xiong, Jianchao Yang, Linjie Yang, Shah Tanmay Anilkumar
-
Patent number: 11645843Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.Type: GrantFiled: January 22, 2021Date of Patent: May 9, 2023Assignee: Snap Inc.Inventors: Samuel Edward Hare, Fedir Poliakov, Guohui Wang, Xuehan Xiong, Jianchao Yang, Linjie Yang, Shah Tanmay Anilkumar
-
Publication number: 20230135137Abstract: A modulated segmentation system can use a modulator network to emphasize spatial prior data of an object to track the object across multiple images. The modulated segmentation system can use a segmentation network that receives spatial prior data as intermediate data that improves segmentation accuracy. The segmentation network can further receive visual guide information from a visual guide network to increase tracking accuracy via segmentation.Type: ApplicationFiled: December 29, 2022Publication date: May 4, 2023Inventors: Linjie Yang, Jianchao Yang, Xuehan Xiong, Yanran Wang
-
Patent number: 11551059Abstract: A modulated segmentation system can use a modulator network to emphasize spatial prior data of an object to track the object across multiple images. The modulated segmentation system can use a segmentation network that receives spatial prior data as intermediate data that improves segmentation accuracy. The segmentation network can further receive visual guide information from a visual guide network to increase tracking accuracy via segmentation.Type: GrantFiled: November 15, 2018Date of Patent: January 10, 2023Assignee: Snap Inc.Inventors: Linjie Yang, Jianchao Yang, Xuehan Xiong, Yanran Wang
-
Publication number: 20210390733Abstract: A method includes receiving video data that includes a series of frames of image data. Here, the video data is representative of an actor performing an activity. The method also includes processing the video data to generate a spatial input stream including a series of spatial images representative of spatial features of the actor performing the activity, a temporal input stream representative of motion of the actor performing the activity, and a pose input stream including a series of images representative of a pose of the actor performing the activity. Using at least one neural network, the method also includes processing the temporal input stream, the spatial input stream, and the pose input stream. The method also includes classifying, by the at least one neural network, the activity based on the temporal input stream, the spatial input stream, and the pose input stream.Type: ApplicationFiled: June 11, 2021Publication date: December 16, 2021Applicant: Google LLCInventors: Yinxiao Li, Zhichao Lu, Xuehan Xiong, Jonathan Huang
-
Publication number: 20210271874Abstract: 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: ApplicationFiled: May 17, 2021Publication date: September 2, 2021Inventors: Xuehan Xiong, Zehao Xue
-
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: 20210216776Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.Type: ApplicationFiled: January 22, 2021Publication date: July 15, 2021Inventors: Samuel Edward Hare, Fedir Poliakov, Guohui Wang, Xuehan Xiong, Jianchao Yang, Linjie Yang, Shah Tanmay Anilkumar
-
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: 10929673Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.Type: GrantFiled: October 16, 2019Date of Patent: February 23, 2021Assignee: Snap Inc.Inventors: Samuel Edward Hare, Fedir Poliakov, Guohui Wang, Xuehan Xiong, Jianchao Yang, Linjie Yang, Shah Tanmay Anilkumar
-
Publication number: 20210027100Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can he assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented. using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.Type: ApplicationFiled: August 13, 2020Publication date: January 28, 2021Inventors: Lidiia Bogdanovych, William Brendel, Samuel Edward Hare, Fedir Poliakov, Guohui Wang, Xuehan Xiong, Jianchao Yang, Linjie Yang