I'm looking for the name of the method (or algorithms family, or research body) used for the smart extend of image surroundings.

For example, the method I'm looking for would take this image:

enter image description here

And smartly extend it into:

enter image description here

So that the grass and the surrounding scenery are all generated to fill the desired area.

Generally speaking, what I'm looking for should smartly generate surroundings including entities such as tree trunks and branches, grass patterns, mountains slopes, clouds patterns, water bodies like puddles, shrubs, stones on ground, and so on.

Also, it would be nice to know how mature is this technology, i.e. how well can different entities be smartly extended.

Note that Seam Carving is a candidate (used in Photoshop under the name Content-Aware Scale (see this for example)), but I'm looking for something smarter, I think, and I'm not really sure if it can do what I'm looking for.


In computer vision, the problem of filling missing parts of an image is called image inpainting; the subtask of filling the surroundings is called image outpainting in [1], which is your problem.

The methods for solving the image outpainting problem are not mature according to the pre-print paper Image Outpainting and Harmonization using Generative Adversarial Networks (2020), which you should read for more info.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.