公开(公告)号：US20220215617A1

公开(公告)日：2022-07-07

申请号：US17701355

申请日：2022-03-22

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yi Song ,  Peiyun Di ,  Wei Xiang ,  Kang Han ,  Bing Wang

IPC: G06T15/20 ,  G06V10/40 ,  G06V10/82

Abstract: A viewpoint image processing method and a related device are provided, and relate to the artificial intelligence/computer vision field. The method includes: obtaining a preset quantity of first viewpoint images; obtaining a geometric feature matrix between the preset quantity of first viewpoint images; generating an adaptive convolution kernel corresponding to each pixel of the preset quantity of first viewpoint images based on the geometric feature matrix and location information of a to-be-synthesized second viewpoint image, where the location information represents a viewpoint location of the second viewpoint image; generating the preset quantity of to-be-processed virtual composite pixel matrices based on the adaptive convolution kernels and the pixels of the preset quantity of existing viewpoint images; and synthesizing the second viewpoint image by using the preset quantity of to-be-processed virtual composite pixel matrices. The method can improve efficiency and quality of synthesizing the second viewpoint image.