公开(公告)号：US20220026982A1

公开(公告)日：2022-01-27

申请号：US17311393

申请日：2019-12-16

Applicant: ZTE CORPORATION

Inventor： Dehui KONG ,  Ke XU ,  Xiao ZHANG ,  Bin HAN ,  Chong XIANG ,  Shuai JIAO ,  Hong WANG ,  Guoning LU ,  Degen ZHEN

IPC: G06F3/01 ,  G09G3/00 ,  G06T3/00

Abstract: A virtual reality display method, device, apparatus and storage medium are provided. The method includes: acquiring multimedia data to be displayed and a visible region of a viewer on a curved display surface, wherein the visible region is obtained by projecting a visible range of the viewer to the curved display surface, and is not larger than a display area of the curved display surface; determining target curvatures of at least two positions in the visible region of the viewer, wherein in the target curvatures, target curvatures of different positions are related to a distance to a center of the visible region of the viewer; adjusting, based on the target curvatures of the at least two positions in the visible region, a curvature of a corresponding position on the curved display surface; and mapping the multimedia data to be displayed to the curved display surface having the adjusted curvature.

公开(公告)号：US20220253668A1

公开(公告)日：2022-08-11

申请号：US17597066

申请日：2020-04-20

Applicant: ZTE CORPORATION

Inventor： Hong WANG ,  Ke XU ,  Guoning LU ,  Degen ZHEN ,  Dehui KONG ,  Xiao ZHANG

IPC: G06N3/04 ,  G06F7/523 ,  G06F7/50 ,  G06F5/01

Abstract: A data processing method and device, a storage medium and an electronic device are disclosed. The method includes: reading M*N feature map data of all input channels and weights of a preset number of output channels, here a value of M*N and a value of the preset number are respectively determined by preset Y*Y weights; inputting the read feature map data and the weights of the preset number of output channels into a multiply-add array of the preset number of output channels for a convolution calculation; here a mode of the convolution calculation includes: not performing the convolution calculation in a case that the feature map data or the weights of the output channels are zero, and selecting one from same values for the convolution calculation in a case that there are a plurality of feature map data with the same values; and outputting a result of the convolution calculation.

公开(公告)号：US20220014745A1

公开(公告)日：2022-01-13

申请号：US17295266

申请日：2019-11-20

Applicant: ZTE Corporation

Inventor： Hong WANG ,  Ke XU ,  Bo HUANG ,  Chengqiang LIU ,  Sheng LUO ,  Guoning LU ,  Degen ZHEN

IPC: H04N19/124 ,  H04N19/60 ,  H04N19/85 ,  H04N19/42

Abstract: Provided are method and device for inverse quantization and inverse transformation and non-transitory computer-readable storage medium. The method includes: performing inverse quantization processing on input data; determining whether secondary inverse transform processing is necessary; performing, in response to determining that the secondary inverse transform processing is necessary, the secondary inverse transform processing on data obtained through the inverse quantization processing, first one-dimensional inverse transform control processing on data obtained through the secondary inverse transform processing, and second one-dimensional inverse transform control processing on data obtained through the first one-dimensional inverse transform control processing; and performing, in response to determining that the secondary inverse transform processing is unnecessary, first one-dimensional inverse transform control processing on the data obtained through the inverse quantization processing, and second one-dimensional inverse transform control processing on the data obtained through the first one-dimensional inverse transform control processing.

公开(公告)号：US20220036506A1

公开(公告)日：2022-02-03

申请号：US17299557

申请日：2019-12-20

Applicant: ZTE Corporation

Inventor： Dehui KONG ,  Ke XU ,  Xiao ZHANG ,  Bin HAN ,  Zhou HAN ,  Hong WANG ,  Guoning LU ,  Long HUANG ,  Sheng LUO

IPC: G06T3/40 ,  G06T5/50 ,  G06K9/62

Abstract: An image reconstruction method, device and apparatus and non-transitory computer-readable storage medium are disclosed. The method may include: determining norms of convolution kernels of each convolutional layer of a deep neural network model; determining the convolution kernels with norms greater than or equal to a preset threshold in each convolutional layer to obtain a target convolution kernel set of each convolutional layer; processing an input image of each convolutional layer by using the convolution kernels in the target convolution kernel set of each convolutional layer respectively, to obtain a first image processing result; obtaining a second image processing result by performing interpolation on an initial image; and determining a fusion result according to the first image processing result and the second image processing result and reconstructing the initial image according to the fusion result.