Patents by Inventor Xiubao Jiang
Xiubao Jiang 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: 11398059Abstract: A mobile device comprises: a mesh loader manages configured to download compressed mesh sequences from a remote server into a local storage buffer; a mesh decoder that is configured to decode compressed mesh sequences into frames of meshes in real-time; a mesh decoder manager that is configured to request compressed mesh sequences from the mesh loader and to request the mesh decoder to decode the compressed mesh sequences; a player manager that is configured to decode texture video and to request corresponding decoded mesh from the mesh decoder manager and to maintain synchronizations between requesting the corresponding decoded mesh and decoding the texture video; and a renderer that is configured to render, using a rendering engine, the decoded mesh on a canvas; and a camera controller that is configured to detect one or more user actions and control a hardware camera in accordance with the one or more user actions.Type: GrantFiled: May 7, 2018Date of Patent: July 26, 2022Assignee: Beijing Dajia Internet Information Technology Co., Ltd.Inventors: Yikai Zhao, Yao Lu, Ziyu Wen, Yi Xu, Xiubao Jiang, Peiyao Zhao, Kunyao Chen
-
Patent number: 11399141Abstract: An example holographic video recording system comprises: a first group of cameras positioned at a first position, a second group of cameras positioned at a second position, and a third group of cameras including a third infrared camera. The first group of cameras includes a first infrared camera and a first color camera; the second group of cameras includes a second infrared camera and a second color camera; and the third group of cameras includes a third infrared camera spatially positioned between the first and second infrared cameras. A depth map may be calculated using the first infrared camera and the second infrared camera in accordance with determining that an object is beyond a predefined distance from the holographic video recording system; or the first infrared camera and the third infrared camera in accordance with determining that the object is within the predefined distance from the holographic video recording system.Type: GrantFiled: October 1, 2020Date of Patent: July 26, 2022Assignee: Beijing Dajia Internet Information Technology Co., Ltd.Inventors: Ziyu Wen, Jisheng Li, Yikai Zhao, Yao Lu, Yi Xu, Zhoutian Feng, Lei Wang, Kunyao Chen, Peiyao Zhao, Xiubao Jiang
-
Publication number: 20210105418Abstract: An example holographic video recording system comprises: a first group of cameras positioned at a first position, a second group of cameras positioned at a second position, and a third group of cameras including a third infrared camera. The first group of cameras includes a first infrared camera and a first color camera; the second group of cameras includes a second infrared camera and a second color camera; and the third group of cameras includes a third infrared camera spatially positioned between the first and second infrared cameras. A depth map may be calculated using the first infrared camera and the second infrared camera in accordance with determining that an object is beyond a predefined distance from the holographic video recording system; or the first infrared camera and the third infrared camera in accordance with determining that the object is within the predefined distance from the holographic video recording system.Type: ApplicationFiled: October 1, 2020Publication date: April 8, 2021Applicant: BEIJING DAJIA INTERNET INFORMATION TECHNOLOGY CO., LTD.Inventors: Ziyu WEN, Jisheng LI, Yikai ZHAO, Yao LU, Yi XU, Zhoutian FENG, Lei WANG, Kunyao CHEN, Peiyao ZHAO, Xiubao JIANG
-
Patent number: 10887569Abstract: Disclosed is a virtual viewpoint synthesis method based on image local segmentation, which relates to the digital image processing technology.Type: GrantFiled: August 14, 2017Date of Patent: January 5, 2021Assignee: PEKING UNIVERSITY SHENZHEN GRADUATE SCHOOLInventors: Ronggang Wang, Xiubao Jiang, Wen Gao
-
Patent number: 10855932Abstract: An example holographic video recording system comprises: a first group of cameras positioned at a first position, a second group of cameras positioned at a second position, and a third group of camera including a third infrared camera. The first group of cameras includes a first infrared camera and a first color camera; the second group of cameras includes a second infrared camera and a second color camera; and the third group of camera includes a third infrared camera spatially positioned between the first and second infrared cameras. A depth map may be calculated using the first infrared camera and the second infrared camera in accordance with determining that an object is beyond a predefined distance from the holographic video recording system; or the first infrared camera and the third infrared camera in accordance with determining that the object is within the predefined distance from the holographic video recording system.Type: GrantFiled: April 5, 2019Date of Patent: December 1, 2020Assignee: Beijing Dajia Internet Information Technology Co., Ltd.Inventors: Ziyu Wen, Jisheng Li, Yikai Zhao, Yao Lu, Yi Xu, Zhoutian Feng, Lei Wang, Kunyao Chen, Peiyao Zhao, Xiubao Jiang
-
Patent number: 10834374Abstract: The disclosure is directed to methods, apparatuses, and devices for synthesizing virtual viewpoint images that are configured for acquiring an original image set, performing stereo matching to original images to obtain a first disparity map set, performing optimization processing to each first disparity map in the first disparity map set to obtain a second disparity map set, determining whether each second disparity map in the second disparity map set has a third disparity map with deep tomography to obtain a first determination result, if the first determination result indicates existence of the third disparity map, segmenting a portion with deep tomography to obtain a corresponding foreground disparity map and a corresponding background disparity map, mapping the second disparity map without deep tomography, the foreground disparity map, the background disparity map, and the portion without deep tomography in the third disparity map according to a first virtual viewpoint to obtain a first virtual viewpointType: GrantFiled: August 28, 2019Date of Patent: November 10, 2020Assignee: PEKING UNIVERSITY SHENZHEN GRADUATE SCHOOLInventors: Ronggang Wang, Xiubao Jiang, Wen Gao
-
Publication number: 20200211230Abstract: A mobile device comprises: a mesh loader manages configured to download compressed mesh sequences from a remote server into a local storage buffer; a mesh decoder that is configured to decode compressed mesh sequences into frames of meshes in real-time; a mesh decoder manager that is configured to request compressed mesh sequences from the mesh loader and to request the mesh decoder to decode the compressed mesh sequences; a player manager that is configured to decode texture video and to request corresponding decoded mesh from the mesh decoder manager and to maintain synchronizations between requesting the corresponding decoded mesh and decoding the texture video; and a renderer that is configured to render, using a rendering engine, the decoded mesh on a canvas; and a camera controller that is configured to detect one or more user actions and control a hardware camera in accordance with the one or more user actions.Type: ApplicationFiled: May 7, 2018Publication date: July 2, 2020Applicant: BEIJING DAJIA INTERNET INFORMATION TECHNOLOGY CO., LTD.Inventors: Yikai ZHAO, Yao LU, Ziyu WEN, Yi XU, Xiubao JIANG, Peiyao ZHAO, Kunyao CHEN
-
Publication number: 20200099911Abstract: Disclosed is a virtual viewpoint synthesis method based on image local segmentation, which relates to the digital image processing technology.Type: ApplicationFiled: August 14, 2017Publication date: March 26, 2020Inventors: Ronggang WANG, Xiubao JIANG, Wen GAO
-
Publication number: 20190387210Abstract: Disclosed are a method, apparatus, and device for synthesizing virtual viewpoint images.Type: ApplicationFiled: August 28, 2019Publication date: December 19, 2019Inventors: Ronggang WANG, Xiubao JIANG, Wen GAO
-
Publication number: 20190311524Abstract: Embodiments of the present disclosure provide a method and apparatus for real-time virtual viewpoint synthesis; during the whole process of synthesizing virtual viewpoint images, unlike the prior art, the method and apparatus for virtual viewpoint synthesis according to the embodiments above do not rely on depth maps and thus effectively avoid the problems incurred by depth-image-based rendering.Type: ApplicationFiled: July 22, 2016Publication date: October 10, 2019Inventors: Ronggang WANG, Jiajia LUO, Xiubao JIANG, Wen GAO
-
Patent number: 10425656Abstract: A video encoding and decoding method, and its inter-frame prediction method, device and system thereof are disclosed. The inter-frame prediction method includes obtaining a motion vector of the current image block and related spatial position of a current pixel, obtaining a motion vector of the current pixel according to the motion vector of the current image block and the related spatial position of the current pixel; and obtaining a predicted value of the current pixel according to the motion vector of the current pixel. The method considers both the motion vector of the current image block and the related spatial position information of the current pixel during inter-frame prediction. The method can accommodate lens distortion characteristics of different images and zoom-in/zoom-out produced when the object moves in pictures, thereby improving the calculation accuracy of pixels' motion vectors, and improving inter-frame prediction performance and compression efficiency in video encoding and decoding.Type: GrantFiled: January 19, 2016Date of Patent: September 24, 2019Assignee: Peking University Shenzhen Graduate SchoolInventors: Zhenyu Wang, Ronggang Wang, Xiubao Jiang, Wen Gao
-
Publication number: 20190253638Abstract: An example holographic video recording system comprises: a first group of cameras positioned at a first positon, a second group of cameras positioned at a second positon, and a third group of camera including a third infrared camera. The first group of cameras includes a first infrared camera and a first color camera; the second group of cameras includes a second infrared camera and a second color camera; and the third group of camera includes a third infrared camera spatially positioned between the first and second infrared cameras. A depth map may be calculated using the first infrared camera and the second infrared camera in accordance with determining that an object is beyond a predefined distance from the holographic video recording system; or the first infrared camera and the third infrared camera in accordance with determining that the object is within the predefined distance from the holographic video recording system.Type: ApplicationFiled: April 5, 2019Publication date: August 15, 2019Applicant: OWLII INC.Inventors: Ziyu Wen, JIisheng LI, Yikai ZHAO, Yao LU, Yi XU, Zhoutian FENG, Lei WANG, Kunyao CHEN, Peiyao ZHAO, Xiubao JIANG
-
Patent number: 10341682Abstract: Methods and devices are disclosed for panoramic video coding and decoding based on multi-mode boundary fill. If a predicted image block of a current image block is obtained by inter-frame prediction. The inter-frame prediction includes a boundary fill step of adaptively selecting a boundary fill method according to coordinates of a reference sample when the reference sample of a pixel in the current image block is outside the boundary of a corresponding reference image, to obtain a sample value of the reference sample. The panoramic video encoding and decoding method and device based on multi-mode boundary fill in the present invention make full use of the characteristic that horizontal image contents in a panoramic video are cyclically connected to optimize an image boundary fill method, such that the encoding can adaptively select a more reasonable boundary fill method according to the coordinates of a reference sample, thereby improving compression efficiency.Type: GrantFiled: January 19, 2016Date of Patent: July 2, 2019Assignee: Peking University Shenzhen Graduate SchoolInventors: Zhenyu Wang, Ronggang Wang, Xiubao Jiang, Wen Gao
-
Publication number: 20190110060Abstract: A video encoding and decoding method, and its inter-frame prediction method, device and system thereof are disclosed. The inter-frame prediction method includes obtaining a motion vector of the current image block and related spatial position of a current pixel, obtaining a motion vector of the current pixel according to the motion vector of the current image block and the related spatial position of the current pixel; and obtaining a predicted value of the current pixel according to the motion vector of the current pixel. The method considers both the motion vector of the current image block and the related spatial position information of the current pixel during inter-frame prediction. The method can accommodate lens distortion characteristics of different images and zoom-in/zoom-out produced when the object moves in pictures, thereby improving the calculation accuracy of pixels' motion vectors, and improving inter-frame prediction performance and compression efficiency in video encoding and decoding.Type: ApplicationFiled: January 19, 2016Publication date: April 11, 2019Inventors: Zhenyu Wang, Ronggang Wang, Xiubao Jiang, Wen Gao
-
Publication number: 20190007702Abstract: Methods and devices are disclosed for panoramic video coding and decoding based on multi-mode boundary fill. If a predicted image block of a current image block is obtained by inter-frame prediction. The inter-frame prediction includes a boundary fill step of adaptively selecting a boundary fill method according to coordinates of a reference sample when the reference sample of a pixel in the current image block is outside the boundary of a corresponding reference image, to obtain a sample value of the reference sample. The panoramic video encoding and decoding method and device based on multi-mode boundary fill in the present invention make full use of the characteristic that horizontal image contents in a panoramic video are cyclically connected to optimize an image boundary fill method, such that the encoding can adaptively select a more reasonable boundary fill method according to the coordinates of a reference sample, thereby improving compression efficiency.Type: ApplicationFiled: January 19, 2016Publication date: January 3, 2019Inventors: Zhenyu Wang, Ronggang Wang, Xiubao Jiang, Wen Gao