Learning Perceptual Aesthetics of 3D Shapes from Multiple Views.

The quantification of 3D shape aesthetics has so far focused on specific shape features and manually defined criteria such as the curvature and the rule of thirds respectively. In this paper, we build a model of 3D shape aesthetics directly from human aesthetics preference data and show it to be well aligned with human perception of aesthetics. To build this model, we first crowdsource a large number of human aesthetics preferences by showing shapes in pairs in an online study and then use the same to build a 3D shape multi-view based deep neural network architecture to allow us learn a measure of 3D shape aesthetics. In comparison to previous approaches, we do not use any pre-defined notions of aesthetics to build our model. Our algorithmically computed measure of shape aesthetics is beneficial to a range of applications in graphics such as search, visualization and scene composition.