Patents by Inventor Xiaoxiang Zuo
Xiaoxiang Zuo 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: 20240303921Abstract: An image acquisition method includes importing a three-dimensional model of an object into a three-dimensional virtual photographing scene having a virtual world coordinate system, determining model position information and model attitude information of the three-dimensional model in the virtual world coordinate system, determining, according to a layout pattern of a plurality of virtual cameras in the three-dimensional virtual photographing scene, camera position information and camera attitude information of each of the plurality of virtual cameras in the virtual world coordinate system, and acquiring, for each of the plurality of virtual cameras, an image of the object from a viewing angle of the virtual camera according to the model position information, the model attitude information, the camera position information, and the camera attitude information.Type: ApplicationFiled: May 17, 2024Publication date: September 12, 2024Inventors: Yiting XU, Yi ZHOU, Xiaoming YU, Yang YI, Chengwei PENG, Feng LI, Xiaoxiang ZUO
-
Publication number: 20240257386Abstract: A video frame processing method, performed by a computer device, includes: receiving video frames carrying noise, wherein the video frames include an object; extracting poses of a part of the object; determining deflection degree values of the part based on the poses; generating a control signal based on the deflection degree values; obtaining updated deflection values based on backlash filtering of the control signal; and performing image processing on the video frames based on the updated deflection values.Type: ApplicationFiled: April 9, 2024Publication date: August 1, 2024Applicant: Tencent Technology (shenzhen) Company LimitedInventors: Yi ZHOU, Xiaoming YU, Yang Yi, Chengwei PENG, Yiting XU, Feng LI, Xiaoxiang ZUO
-
Publication number: 20240257319Abstract: An image noise reduction method including: obtaining a first image to be processed and a second image as a reference image; obtaining a block of the first image by dividing the first image; determining a motion intensity of the block based on the second image; obtaining filter coefficient description information matching the motion intensity based on: a first pixel difference of a first pixel point value of the first image and a second pixel point value of the second image, and a filter coefficient; obtaining a target pixel difference between a third pixel point value of the block and a fourth pixel point value of the second image; determining a target filter coefficient corresponding to the target pixel difference based on the filter coefficient description information; and determining a target noise reduction image of the first image based on the target filter coefficient.Type: ApplicationFiled: April 9, 2024Publication date: August 1, 2024Applicant: Tencent Technology (Shenzhen) Company LimitedInventors: Chengwei Peng, Yang Yi, Yi Zhou, Xiaoming Yu, Yiting Xu, Feng Li, Xiaoxiang Zuo
-
Patent number: 11989350Abstract: A hand key-point recognition model training method is provided for a model training device. The method includes: converting a sample virtual image into an emulation image through a Cycle-GAN model, the sample virtual image being an image generated through three-dimensional modeling, and the sample virtual image including key-point coordinates corresponding to hand key-points, and the emulation image being used for emulating an image acquired in a real scenario; extracting a hand image in the emulation image; and training a hand key-point recognition model according to the hand image in the emulation image and the key-point coordinates, the hand key-point recognition model being used for outputting hand key-point coordinates of a hand in a real image according to the inputted real image.Type: GrantFiled: August 24, 2020Date of Patent: May 21, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Yang Yi, Shijie Zhao, Feng Li, Xiaoxiang Zuo
-
Publication number: 20230222838Abstract: This disclosure provides a method and a system for detecting and recognizing a target object in a real-time video. The method includes: determining whether a target object recognition result RX-1 of a previous frame of image of a current frame of image is the same as a target object recognition result RX-2 of a previous frame of image of the previous frame of image; performing target object position detection in the current frame of image by using a first-stage neural network to obtain a position range CX of a target object in the current frame of image when the two recognition results RX-1 and RX-2 are different; or determining a position range CX of a target object in the current frame of image according to a position range CX-1 of the target object in the previous frame of image when the two recognition results RX-1 and RX-2 are the same; and performing target object recognition in the current frame of image according to the position range CX by using a second-stage neural network.Type: ApplicationFiled: February 27, 2023Publication date: July 13, 2023Applicant: Tencent Technology (Shenzhen) Company LimitedInventors: Jun CHENG, Haibao SHANG, Feng LI, Haoyuan LI, Xiaoxiang ZUO
-
Patent number: 11625921Abstract: This disclosure provides a method and a system for detecting and recognizing a target object in a real-time video. The method includes: determining whether a target object recognition result RX-1 of a previous frame of image of a current frame of image is the same as a target object recognition result RX-2 of a previous frame of image of the previous frame of image; performing target object position detection in the current frame of image by using a first-stage neural network to obtain a position range CX of a target object in the current frame of image when the two recognition results RX-1 and RX-2 are different; or determining a position range CX of a target object in the current frame of image according to a position range CX-1 of the target object in the previous frame of image when the two recognition results RX-1 and RX-2 are the same; and performing target object recognition in the current frame of image according to the position range CX by using a second-stage neural network.Type: GrantFiled: September 4, 2020Date of Patent: April 11, 2023Assignee: Tencent Technology (Shenzhen) Company LimitedInventors: Jun Cheng, Haibao Shang, Feng Li, Haoyuan Li, Xiaoxiang Zuo
-
Publication number: 20230082715Abstract: A method for training an image processing model includes: acquiring a to-be-corrected eye image set matching a usage environment of the image processing model; performing style transfer on to-be-corrected eye images in the to-be-corrected eye image set through a style transfer network in the image processing model, to obtain a target eye image; acquiring a training sample matching the usage environment of the image processing model based on the to-be-corrected eye images and the target eye image, the training sample including object eye images matching different gaze positions; and training a correction network in the image processing model through the training sample matching the usage environment of the image processing model, to obtain a model update parameter matching the correction network, and generating a trained image processing model based on the model update parameter.Type: ApplicationFiled: November 22, 2022Publication date: March 16, 2023Inventors: Xiaoming YU, Yi ZHOU, Yang YI, Juanhui TU, Feng LI, Xiaoxiang ZUO
-
Patent number: 11366528Abstract: This application discloses a method, an apparatus, and a storage medium for gesture movement recognition.Type: GrantFiled: August 27, 2020Date of Patent: June 21, 2022Assignee: Tencent Technology (Shenzhen) Company LimitedInventors: Shijie Zhao, Feng Li, Xiaoxiang Zuo, Jun Cheng
-
Patent number: 11367196Abstract: This application relates to an image processing method and apparatus, a storage medium, and a computer device. The method includes obtaining acquired image frames; identifying, in each obtained image frame, a target area and a reference area that are obtained through image semantic segmentation; detecting, when a location relationship between the target area and the reference area in an obtained first image frame meets an action start condition and a location relationship between the target area and the reference area in an obtained second image frame meets an action end condition, an action to trigger adding an additional element, the second image frame being acquired after the first image frame; obtaining the additional element when the triggering action is detected; and adding the additional element to image frames acquired after the second image frame.Type: GrantFiled: August 19, 2020Date of Patent: June 21, 2022Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Jun Cheng, Ying Zhu, Haoyuan Li, Feng Li, Xiaoxiang Zuo
-
Patent number: 11281925Abstract: A method for recognizing object nodes in an image includes: performing image detection on an original image, to determine a target image region that comprises a target image object, the original image being a two-dimensional image; performing image cropping on the original image according to the target image region, to obtain a subimage comprising the target image object; and performing node recognition on the subimage based on a preset node recognition model, to obtain image position information of each node of the target image object in the original image.Type: GrantFiled: June 15, 2020Date of Patent: March 22, 2022Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Feng Li, Xiaoxiang Zuo, Haoyuan Li, Jun Cheng
-
Patent number: 11176404Abstract: An embodiment of this application provides an image object detection method. The method may include obtaining a detection image, an n-level deep feature map framework, and an m-level non-deep feature map framework. The method may further include extracting deep feature from an (i?1)-level feature of the detection image using an i-level deep feature map framework, to obtain an i-level feature of the detection image. The method may further include extracting non-deep feature from a (j?1+n)-level feature of the detection image using a j-level non-deep feature map framework, to obtain a (j+n)-level feature of the detection image. The method may further include performing information regression operation on an a-level feature to an (m+n)-level feature of the detection image, to obtain an object type information and an object position information of an object in the detection image. The a is an integer less than n and greater than or equal to 2.Type: GrantFiled: August 31, 2020Date of Patent: November 16, 2021Assignee: Tencent Technology (Shenzhen) Company LimitedInventors: Shijie Zhao, Feng Li, Xiaoxiang Zuo
-
Publication number: 20200401812Abstract: This disclosure provides a method and a system for detecting and recognizing a target object in a real-time video. The method includes: determining whether a target object recognition result RX-1 of a previous frame of image of a current frame of image is the same as a target object recognition result RX-2 of a previous frame of image of the previous frame of image; performing target object position detection in the current frame of image by using a first-stage neural network to obtain a position range CX of a target object in the current frame of image when the two recognition results RX-1 and RX-2 are different; or determining a position range CX of a target object in the current frame of image according to a position range CX-1 of the target object in the previous frame of image when the two recognition results RX-1 and RX-2 are the same; and performing target object recognition in the current frame of image according to the position range CX by using a second-stage neural network.Type: ApplicationFiled: September 4, 2020Publication date: December 24, 2020Applicant: Tencent Technology (Shenzhen) Company LimitedInventors: Jun CHENG, Haibao SHANG, Feng LI, Haoyuan LI, Xiaoxiang ZUO
-
Publication number: 20200394433Abstract: An embodiment of this application provides an image object detection method. The method may include obtaining a detection image, an n-level deep feature map framework, and an m-level non-deep feature map framework. The method may further include extracting deep feature from an (i?1)-level feature of the detection image using an i-level deep feature map framework, to obtain an i-level feature of the detection image. The method may further include extracting non-deep feature from a (j?1+n)-level feature of the detection image using a j-level non-deep feature map framework, to obtain a (j+n)-level feature of the detection image. The method may further include performing information regression operation on an a-level feature to an (m+n)-level feature of the detection image, to obtain an object type information and an object position information of an object in the detection image. The a is an integer less than n and greater than or equal to 2.Type: ApplicationFiled: August 31, 2020Publication date: December 17, 2020Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Shijie ZHAO, Feng LI, Xiaoxiang ZUO
-
Publication number: 20200393911Abstract: This application discloses a method, an apparatus, and a storage medium for gesture movement recognition.Type: ApplicationFiled: August 27, 2020Publication date: December 17, 2020Applicant: Tencent Technology (Shenzhen) Company LimitedInventors: Shijie ZHAO, Feng LI, Xiaoxiang ZUO, Jun CHENG
-
Publication number: 20200387698Abstract: A hand key-point recognition model training method is provided for a model training device. The method includes: converting a sample virtual image into an emulation image through a Cycle-GAN model, the sample virtual image being an image generated through three-dimensional modeling, and the sample virtual image including key-point coordinates corresponding to hand key-points, and the emulation image being used for emulating an image acquired in a real scenario; extracting a hand image in the emulation image; and training a hand key-point recognition model according to the hand image in the emulation image and the key-point coordinates, the hand key-point recognition model being used for outputting hand key-point coordinates of a hand in a real image according to the inputted real image.Type: ApplicationFiled: August 24, 2020Publication date: December 10, 2020Inventors: Yang YI, Shijie ZHAO, Feng LI, Xiaoxiang ZUO
-
Publication number: 20200380690Abstract: This application relates to an image processing method and apparatus, a storage medium, and a computer device. The method includes obtaining acquired image frames; identifying, in each obtained image frame, a target area and a reference area that are obtained through image semantic segmentation; detecting, when a location relationship between the target area and the reference area in an obtained first image frame meets an action start condition and a location relationship between the target area and the reference area in an obtained second image frame meets an action end condition, an action to trigger adding an additional element, the second image frame being acquired after the first image frame; obtaining the additional element when the triggering action is detected; and adding the additional element to image frames acquired after the second image frame.Type: ApplicationFiled: August 19, 2020Publication date: December 3, 2020Inventors: Jun CHENG, Ying ZHU, Haoyuan LI, Feng LI, Xiaoxiang ZUO
-
Publication number: 20200311453Abstract: A method for recognizing object nodes in an image includes: performing image detection on an original image, to determine a target image region that comprises a target image object, the original image being a two-dimensional image; performing image cropping on the original image according to the target image region, to obtain a subimage comprising the target image object; and performing node recognition on the subimage based on a preset node recognition model, to obtain image position information of each node of the target image object in the original image.Type: ApplicationFiled: June 15, 2020Publication date: October 1, 2020Inventors: Feng LI, Xiaoxiang ZUO, Haoyuan LI, Jun CHENG
-
Patent number: 10742574Abstract: A method and device are described for implementing instant communication. Information indicating that a first user is logged into an instant communication interface is obtained. On-line users are displayed to the first user in response to the login of the first user. A first user selects an object to follow from the on-line users and, information about the selected object to follow is received in response to the first user selecting the object to follow from the on-line users. The first user may be set into a first instant communication room in which the selected object to follow resides, for performing instant communication. The device includes: an obtaining module, a displaying module and a processing module. In this manner communication between strangers is facilitated and the efficiency of making friends is enhanced.Type: GrantFiled: October 26, 2017Date of Patent: August 11, 2020Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Yuhuang Li, Xingyi Zhang, Xiaoxiang Zuo, Xin Xie, Shiqi Xu, Xianxian Zhang
-
Publication number: 20180048597Abstract: A method and device are described for implementing instant communication. Information indicating that a first user is logged into an instant communication interface is obtained. On-line users are displayed to the first user in response to the login of the first user. A first user selects an object to follow from the on-line users and, information about the selected object to follow is received in response to the first user selecting the object to follow from the on-line users. The first user may be set into a first instant communication room in which the selected object to follow resides, for performing instant communication. The device includes: an obtaining module, a displaying module and a processing module. In this manner communication between strangers is facilitated and the efficiency of making friends is enhanced.Type: ApplicationFiled: October 26, 2017Publication date: February 15, 2018Inventors: Yuhuang LI, Xingyi ZHANG, Xiaoxiang ZUO, Xin XIE, Shiqi XU, Xianxian ZHANG
-
Patent number: 9832144Abstract: A method and device are described for implementing instant communication. Information indicating that a first user is logged into an instant communication interface is obtained. On-line users are displayed to the first user in response to the login of the first user. A first user selects an object to follow from the on-line users and, information about the selected object to follow is received in response to the first user selecting the object to follow from the on-line users. The first user may be set into a first instant communication room in which the selected object to follow resides, for performing instant communication. The device includes: an obtaining module, a displaying module and a processing module. In this manner communication between strangers is facilitated and the efficiency of making friends is enhanced.Type: GrantFiled: May 6, 2014Date of Patent: November 28, 2017Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Yuhuang Li, Xingyi Zhang, Xiaoxiang Zuo, Xin Xie, Shiqi Xu, Xianxian Zhang