| CPC G06T 7/40 (2013.01) [G06T 7/10 (2017.01); G06V 10/44 (2022.01); G06V 10/771 (2022.01); G06V 10/82 (2022.01); G06T 2207/20016 (2013.01)] | 20 Claims |

|
1. An image processing method, wherein the method is implemented using a neural network, and the method comprises:
obtaining a dependency relationship between features of texture primitives of an image based on direction information and a multi-scale feature map of the image, wherein the multi-scale feature map comprises features of a plurality of texture primitives of the image on a plurality of different scales, and the direction information comprises one or more directions;
obtaining at least one group of texture features of the image based on a feature map of the image on at least one scale of the plurality of different scales, wherein the at least one group of texture features of the image is obtained based on the feature map of the image on the at least one scale;
obtaining a texture representation result of the image based on the dependency relationship and the at least one group of texture features; and
processing the image based on the texture representation result of the image.
|