Abstract: A region of an image on which a content aware fill operation is to be performed is identified by a device, the content aware fill operation replacing pixel values in the region based on pixel values from one or more other regions. The device generates a reduced-size version of the image by down sampling the image, and sends the reduced-size version of the image to a remote service. The remote service generates a mapping indicating which pixels in the reduced-size version of the image are to be used as the values of which other pixels in the region of the reduced-size version of the image. The mapping is compressed and returned to the device. The device decompresses the mapping and up samples the mapping. An output image is generated based on the originally obtained image, the up sampled mapping, and an indication of the region.