Image processing method and related device

An electronic device, comprising:

• a memory storing one or more instructions;
• and
• at least one processor communicatively coupled to the memory, and configured to execute the one or more instructions to:
• acquire a target image based on an editing operation on an original image, wherein the target image comprises an unknown region formed by the editing operation;
• perform a filling processing operation on the target image to obtain a filled image comprising a target region, wherein the target region corresponds to the unknown region;
• identify a target image patch comprising at least a portion of the target region in the filled image;
• tile the target image patch to generate a tile image with a predetermined third size comprising a plurality of tiles corresponding to the target image patch;
• obtain a similarity value between the target image patch and at least one image patch from the filled image by inputting the tile image into a first artificial intelligence (AI) model;
• determine a residual patch associated with an image patch among the at least one image patch as a target residual patch associated with the target image patch based on the similarity value, wherein the residual patch comprises high frequency texture information associated with the image patch;
• and
• generate a processing result image based on the target residual patch and the filled image.

A non-transitory computer readable storage medium storing a program to be executable by at least one processor to perform an image processing method, wherein the image processing method comprises:

• acquiring a target image based on an editing operation on an original image, wherein the target image comprises an unknown region formed by the editing operation;
• performing a filling processing operation on the target image to obtain a filled image comprising a target region, wherein the target region corresponds to the unknown region;
• identifying a target image patch comprising at least a portion of the target region in the filled image;
• tiling the target image patch to generate a tile image with a predetermined third size comprising a plurality of tiles corresponding to the target image patch;
• obtaining a similarity value between the target image patch and at least one image patch from the filled image by inputting the tile image into a first artificial intelligence (AI) model;
• determining a residual patch associated with an image patch among the at least one image patch as a target residual patch associated with the target image patch based on the similarity value, wherein the residual patch comprises high frequency texture information associated with the image patch;
• and
• generating a processing result image based on the target residual patch and the filled image.