-
公开(公告)号：US20240249503A1
公开(公告)日：2024-07-25
申请号：US18594113
申请日：2024-03-04
发明人： Xinghua JIANG , Hao LIU , Xin LI , Deqiang JIANG
CPC分类号： G06V10/764 , G06V10/26 , G06V10/42 , G06V10/44 , G06V10/7715 , G06V10/806 , G06V10/82
摘要： Disclosed in this application is an image processing method and a related apparatus. The method includes performing vectorization on a to-be-processed image, to obtain an image representation vector; performing feature mapping on the image representation vector to obtain an image feature, including: performing, at a same network layer of a network block, global feature mapping on input content to obtain a global feature, and performing local feature mapping on the input content to obtain a local feature, the input content being obtained based on the image representation vector; performing feature fusion on the global feature and the local feature to obtain a fused feature; obtaining an image feature based on the fused feature; and performing category prediction by using a classification module in the image classification model based on the image feature, to obtain a classification result of the to-be-processed image.
-
公开(公告)号：US20200043142A1
公开(公告)日：2020-02-06
申请号：US16582903
申请日：2019-09-25
发明人： Hao LIU
摘要： This application discloses an image processing method and apparatus, a storage medium, and an electronic apparatus. The image processing method includes performing edge expansion on an object in a scene according to a location parameter to obtain a profile of an expanded object, the location parameter being a relative location parameter of the object in the scene from a viewpoint; identifying a circle of confusion (COC) value of a vertex of the object as a COC value of a corresponding vertex of the profile of the expanded object; determining a color of each pixel of the expanded object according to the COC value of the corresponding vertex and a texture of the object in the scene; and displaying the expanded object based on the color of each pixel.
-
公开(公告)号：US20190333201A1
公开(公告)日：2019-10-31
申请号：US16506712
申请日：2019-07-09
发明人： Hao LIU
摘要： The present disclosure discloses an image display method and apparatus in a virtual reality (VR) device. The method includes: obtaining a first image to be displayed by the VR device, an edge of a target object in the first image having an aliasing shape, the VR device being provided with an electromagnetic vibrator, and the electromagnetic vibrator being configured to control the first image to move by a first distance along a first direction; obtaining a second image after the electromagnetic vibrator vibrates, the second image being an image obtained after the first image is moved by the first distance along the first direction; performing a superimposition operation on the first image and the second image to obtain a target image, an edge of the target object in the target image changing from the aliasing shape to a smooth shape; and displaying the target image in the VR device.
-
4.发明公开公开(公告)号：US20240296652A1
公开(公告)日：2024-09-05
申请号：US18662871
申请日：2024-05-13
发明人： Yunhao WANG , Tinghao YU , Shaohua CHEN , Hao LIU , Haodi HOU
CPC分类号： G06V10/462 , G06V10/25 , G06V10/42 , G06V10/806
摘要： A content recognition method is performed by a computer device, which relate to the field of machine learning. The method includes: acquiring an image; recognizing a target region from the image by performing saliency detection on the image; extracting a key point feature representation corresponding to an image key point in the image; performing pooling on an image feature representation corresponding to the image to obtain a global feature representation; and recognizing a category of target content comprised in the target region based on the global feature representation and the key point feature representation.
-
5.发明公开公开(公告)号：US20240311976A1
公开(公告)日：2024-09-19
申请号：US18671582
申请日：2024-05-22
发明人： Yuanyuan ZHAO , Jian ZHANG , Yingying FU , Hao LIU , Chen LI
IPC分类号： G06T5/60 , G06T5/50 , G06V10/26 , G06V10/764 , G06V10/774 , G06V10/776 , G06V10/82
CPC分类号： G06T5/60 , G06T5/50 , G06V10/26 , G06V10/764 , G06V10/774 , G06V10/776 , G06V10/82 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06T2207/20221
摘要： This application relates to an image correction model training method including obtaining a training image, and performing random data distortion on the training image to obtain a distorted image and distortion parameter information; inputting the distorted image into an initial image correction model to predict a correction parameter, to obtain initial correction parameter information, and performing image correction on the distorted image to obtain an initial corrected image; calculating a loss between the initial correction parameter information and correction parameter information corresponding to the distortion parameter information, to obtain parameter loss information, and calculating a loss between the training image and the initial corrected image to obtain image loss information; updating the initial image correction model to obtain an updated image correction model; and performing training and obtaining the updated image correction model iteratively, until a target image correction model is obtained when a training completion condition is reached.
-
-
-
-
搜索结果
5 条记录 (耗时 0.017 秒)
