And you, too, show this bug, dear AiDon. The problem is that you do not understand that this is a bug, the correction of which must be requested from the developers.
I already wrote about this, but I will write again. Only developers know what resolution the incoming image must-have for the algorithm to recognize it as satisfactory and adequately increase it.
If you plunge into history, Bayer filters and the like, it turns out that the actual resolution of the incoming image is much less than you think. Therefore, the blurred image stretched by the camera, and the algorithm cannot swallow such a soapy picture.
If you can reduce the image to real resolution, where each pixel carries real information, then the algorithm will work much better.
I understand your pain AiDon. The developers did not know or did not want to know this, that now orders for designers are made by people who are far from graphics. They take pictures on an old iPhone 5 and then send a photo with compression through Viber, after which only 1280 pixels and the wildest noises of the mobile matrix are left from the picture. And they are sure that they sent a beautiful image because on their phone they can still see it, but it doesn’t matter how it looks in Viber after compression. And not a single AI algorithm is ready for this.
