There are several “advices” on photographic forum on how to take a better photo and how to make a photo even better in post-processing. Yet, in the end, you look at several photos and you pick up one as the best one and it is difficult to put in words “why” it is really the best (at least for you). There is a lot a subjective judgement in classifying the beauty of a photo.
Google researchers have developed a (soft) robot and taught it to recognise good photos among the hundreds of million photos taken by StreetView and to post process them to make they look like professional photos. The results are (at least to me) quite impressive.
Although it is clear that the robot applies, in making its selection, some generally accepted criteria like the rule of thirds, focus on the foreground, presence of a line guiding the eye from the front of the image to the far distance, one has to admit that the choices made and the way the photo has been post processed goes beyond technicalities. Indeed, the robot used an aesthetic filter trained by AI deep learning algorithms.
To test the result of the work performed by the robot the Google team submitted in a blind test the photos produced by the robot mixed with several others taken by a variety of photographer and submitted them to professional photographers evaluation. The result indicates that 40% of the photos produced by the robot are ranked in the semi-pro to pro quality, quite impressive!