Abstract: A computer-implemented method for high resolution image inpainting comprising the following steps: providing a high resolution input image, providing at least one inpainting mask, selecting at least one rectangular sub-region of the input image and at least one aligned rectangular subregion of the inpainting mask such that the rectangular subregion of the input image encompasses at least one set of pixels to be removed and synthetized, the at least one sub-region of the input image and its corresponding aligned subregion of the inpainting mask having identical minimum possible size and a position for which a calculated information gain does not decrease, processing the sub-region of the input image and its corresponding aligned subregion of the inpainting mask by a machine learning model, generating an output high resolution image comprising the inpainted sub-region.