-
公开(公告)号：US09811718B2
公开(公告)日：2017-11-07
申请号：US15129567
申请日：2014-04-11
发明人： Yi Sun , Xiaogang Wang , Xiaoou Tang
CPC分类号： G06K9/00281 , G06K9/00288 , G06K9/4628 , G06K9/52 , G06K9/6215 , G06K9/6269 , G06K2009/4666 , G06N3/08
摘要： Disclosed are a method and an apparatus for face verification. The apparatus comprises a feature extracting unit configured to extract HIFs (Hidden Identity Features) for different regions of faces by using differently trained ConvNets, wherein last hidden layer neuron activations of said ConvNets are considered as the HIFs. The apparatus further comprises a verification unit configured to concatenate the extracted HIFs of each of the faces to form a feature vector, and then compare two of the formed feature vectors to determine if they are from the same identity or not.
-
公开(公告)号：US11741583B2
公开(公告)日：2023-08-29
申请号：US17696240
申请日：2022-03-16
发明人： Mingyang Huang , Wanzeng Fu , Jianping Shi , Yi Qu
CPC分类号： G06T5/005 , G06T5/002 , G06T5/20 , G06T7/90 , G06V10/56 , G06V40/162 , G06V40/165 , G06V40/171 , G06T2207/30201
摘要： A face image processing method and apparatus, an electronic device, and a storage medium are provided. The method includes: obtaining face key points and a face deflection angle in a face image; determining a submalar triangle center in the face image according to the face key points and the face deflection angle; determining a submalar triangle region in the face image according to the face key points and the submalar triangle center; and performing color filling on the submalar triangle region. By means of the present disclosure, a submalar triangle region can be accurately positioned, and submalar triangle filling is performed based on the accurately positioned submalar triangle region, thereby obtaining a more natural filling effect.
-
公开(公告)号：US11544820B2
公开(公告)日：2023-01-03
申请号：US17072527
申请日：2020-10-16
发明人： Rui Xu , Xiaoxiao Li , Bolei Zhou , ChenChange Loy
IPC分类号： G06T5/00
摘要： The present disclosure relates to a video repair method and apparatus, an electronic device, and a storage medium. The method includes: acquiring first forward optical flows and first reverse optical flows between adjacent images among continuous multiple frames of images; respectively performing optical flow optimization processing on the first forward optical flows and the first reverse optical flows to obtain second forward optical flows corresponding to the first forward optical flows and second reverse optical flows corresponding to the first reverse optical flows; performing forward and reverse conduction optimization on the continuous multiple frames of images by utilizing the second forward and the second reverse optical flows, respectively, until all the images in the optimized continuous multiple frames of images satisfy repair requirements; and obtaining repaired images of the continuous multiple frames of images according to the optimized images obtained by the forward conduction optimization and the reverse conduction optimization.
-
公开(公告)号：US11538207B2
公开(公告)日：2022-12-27
申请号：US17073769
申请日：2020-10-19
发明人： Tong Li , Wentao Liu , Chen Qian
摘要： An image processing method and apparatus, a device, and a storage medium are provided. The image processing method includes: obtaining key points of a reference region of an object in an image; determining the orientation of the reference region according to the key points of the reference region; and performing deformation processing on a region to be adjusted of the object based on the orientation of the reference region, where the region to be adjusted is the same as or different from the reference region.
-
公开(公告)号：US11521389B2
公开(公告)日：2022-12-06
申请号：US16881143
申请日：2020-05-22
发明人： Qinqin Xu , Zhanpeng Li
摘要： A method for generating a special effect program file package and a method for generating a special effect are provided. The method for generating a special effect program file package includes: importing a sub-material; obtaining a parameter value of a playback parameter of the sub-material and establishing a correspondence between a display position of the sub-material and at least one predetermined key point; and generating a special effect program file package according to the sub-material, the correspondence and the parameter value. The method for generating a special effect includes: importing a special effect program file package; obtaining a parameter value of a playback parameter of a sub-material in the special effect program file package; performing key point detection on a video image; and generating a special effect of the sub-material on the video image based on the detected key point and the parameter value of the playback parameter.
-
76.发明授权公开(公告)号：US11475624B2
公开(公告)日：2022-10-18
申请号：US17552621
申请日：2021-12-16
发明人： Pengrui Wang , Chunze Lin , Quan Wang , Chen Qian
摘要： Provided are a method and apparatus for generating a three-dimensional model. The method includes following. A first image containing a first face is acquired. First point cloud data including contour information of the first face is determined based on the first image. First albedo information of the first face and second point cloud data including detail information of the first face are determined based on the first point cloud data and the first image. A three-dimensional model of the first face is generated based on the first albedo information and the second point cloud data.
-
公开(公告)号：US11455782B2
公开(公告)日：2022-09-27
申请号：US16868427
申请日：2020-05-06
摘要： Embodiments of the present disclosure disclose a target detecting method and apparatus, a training method, an electronic device, and a medium. The target detecting method includes: separately extracting, by means of a neural network, characteristics of a template frame and a detection frame, where the template frame is a detection box image of a target object, and the template frame is smaller than the detection frame in image size; obtaining a classification weight and a regression weight of a local region detector based on the characteristic of the template frame; inputting the characteristic of the detection frame into the local region detector to obtain classification results and regression results of multiple alternative boxes output by the local region detector; and obtaining a detection box for the target object in the detection frame according to the classification results and regression results of the multiple alternative boxes output by the local region detector. The embodiments of the present disclosure improve the speed and accuracy in target tracking.
-
公开(公告)号：US20220301220A1
公开(公告)日：2022-09-22
申请号：US17834021
申请日：2022-06-07
发明人： Liwei ZHANG
摘要： A method for displaying a target object, an electronic device, and a non-transitory storage medium are provided. The method includes: displaying at least one to-be-analyzed object in response to a first operation for the target object; obtaining an anchor point for determining one of the at least one to-be-analyzed object, in response to a second operation for the target object; determining, according to acquired object distribution images and the anchor point, a range of area where the current to-be-analyzed object corresponding to the anchor point is located in the target object.
-
79.发明授权公开(公告)号：US11423625B2
公开(公告)日：2022-08-23
申请号：US17134811
申请日：2020-12-28
发明人： Xinru Hou , Qing Luan , Chongshan Sheng , Fei Jiao , Huafu Ou , Shengchuan Shi , Nan Wang , Hanqing Jiang
摘要： An Augmented Reality (AR) scene image processing method, an electronic device and a storage medium are provided. The method includes that: shooting pose data of an AR device is acquired; presentation special effect data of a virtual object corresponding to the shooting pose data in a reality scene is acquired based on the shooting pose data and position pose data of the virtual object in a three-dimensional scene model representing the reality scene; and an AR scene image is displayed through the AR device based on the presentation special effect information.
-
公开(公告)号：US20220222922A1
公开(公告)日：2022-07-14
申请号：US17711627
申请日：2022-04-01
发明人： Xinge ZHU , Tai WANG , Yan XU , Jianping SHI , Dahua LIN
IPC分类号： G06V10/764 , G06V10/74 , G06V10/46 , G06T7/68
摘要： Object recognition methods and devices, and storage media are provided. In one aspect, an object recognition method includes: acquiring to-be-processed point cloud data and processing the to-be-processed point cloud data to obtain target point cloud data, the to-be-processed point cloud data including point cloud data of an to-be-recognized object; recognizing the to-be-recognized object from the target point cloud data and determining a target feature of the to-be-recognized object; and determining, according to the target feature, a target category to which the to-be-recognized object belongs among a plurality of categories to obtain a recognition result for the to-be-recognized object. The recognition result includes at least the target category.
-
-
-
-
-
-
-
-
-
搜索结果
355 条记录 (耗时 0.031 秒)
