In this semester project we develop an automated system to rank panoramas captured by the EPFL Livecam according to how visually appealing they are. In other words, a system able to predict an average of the rating of human users for such panoramas. As a way to achieve it, we explore the capabilities of deep neural networks to solve the problem given three different datasets: a general dataset for aesthetics (Photo.net), a custom dataset built with panoramas extracted from Flickr, and a domain specific dataset built from evaluated panoramas extracted from the camera itself. We show that shallow network architectures, limited computational resources, and scarce data (as opposed to highlighted literature on deep nets), are sufficient to provide satisfactory rankings. Finally a roadmap for further development is presented.

LCAV1558050917