-
Patent Agency Ranking
公开(公告)号：US20220392251A1
公开(公告)日：2022-12-08
申请号：US17820108
申请日：2022-08-16
Inventor： Shichang Zhang , Ziyuan Guo , Yafei Zhao , Chao Chen , Xirui Fan
Abstract: A method for generating an object model includes: obtaining an initial morphable model; obtaining a plurality of initial images of an object, and depth images corresponding to the plurality of initial images; obtaining a plurality of target topological images by processing the plurality of initial images based on the depth images; obtaining a plurality of models to be synthesized by processing the initial morphable model based on the plurality of target topological images; and generating a target object model based on the plurality of models to be synthesized.
-
公开(公告)号：US11521653B2
公开(公告)日：2022-12-06
申请号：US17541822
申请日：2021-12-03
Inventor： Yafei Zhao , Shichang Zhang , Ziyuan Guo , Chao Chen
IPC: G11B27/031 , G06V20/40 , G11B27/00
Abstract: A video sequence layout method, electronic device and storage medium are provided, and relate to fields of deep learning, virtual reality, cloud computing, video layout processing and the like. The method includes: acquiring a first video sequence, the first video sequence including a main sequence for describing a first posture of a human body and a subordinate sequence for describing a plurality of second postures of the human body; extracting the main sequence and the subordinate sequence from the first video sequence; and in a case that it is detected that a sequencing identification frame exists in the first video sequence, performing random mixed sequencing processing on video frames in the main sequence and the subordinate sequence based on the sequencing identification frame and taking a sequence combination obtained by the random mixed sequencing processing as a second video sequence.
-
公开(公告)号：US12175792B2
公开(公告)日：2024-12-24
申请号：US17820108
申请日：2022-08-16
Inventor： Shichang Zhang , Ziyuan Guo , Yafei Zhao , Chao Chen , Xirui Fan
Abstract: A method for generating an object model includes: obtaining an initial morphable model; obtaining a plurality of initial images of an object, and depth images corresponding to the plurality of initial images; obtaining a plurality of target topological images by processing the plurality of initial images based on the depth images; obtaining a plurality of models to be synthesized by processing the initial morphable model based on the plurality of target topological images; and generating a target object model based on the plurality of models to be synthesized.
-
公开(公告)号：US20240420403A1
公开(公告)日：2024-12-19
申请号：US18747188
申请日：2024-06-18
Inventor： Xirui Fan , Yafei Zhao , Yi Chen , Zongcai Du , Zhiqiang Wang
Abstract: A method for generating a human face video, an apparatus for generating a human face video, includes: obtaining a mouth-shape multimedia resource and a reference human face image of a target object; obtaining a reference style vector of the target object; for each resource frame in the mouth-shape multimedia resource, obtaining a mouth-shape driving feature by performing a feature extraction process on the resource frame; generating a stylistic human face image corresponding to the resource frame according to the mouth-shape driving feature, the reference human face image, and the reference style vector; and determining a stylistic human face video of the target object.
-
公开(公告)号：US20220093133A1
公开(公告)日：2022-03-24
申请号：US17541822
申请日：2021-12-03
Inventor： Yafei Zhao , Shichang Zhang , Ziyuan Guo , Chao Chen
IPC: G11B27/031 , G06V20/40 , G11B27/00
Abstract: A video sequence layout method, electronic device and storage medium are provided, and relate to fields of deep learning, virtual reality, cloud computing, video layout processing and the like. The method includes: acquiring a first video sequence, the first video sequence including a main sequence for describing a first posture of a human body and a subordinate sequence for describing a plurality of second postures of the human body; extracting the main sequence and the subordinate sequence from the first video sequence; and in a case that it is detected that a sequencing identification frame exists in the first video sequence, performing random mixed sequencing processing on video frames in the main sequence and the subordinate sequence based on the sequencing identification frame and taking a sequence combination obtained by the random mixed sequencing processing as a second video sequence.
-
-
-
-
Search Results
5
records
(took 0.033 seconds)
