Dev, Kapil and Lau, Manfred (2020) Learning Perceptual Aesthetics of 3D Shapes from Multiple Views. IEEE Computer Graphics & Applications. ISSN 0272-1716 (Accepted for Publication)
Preview |
Text
CGA_Aesthetics.pdf - Accepted Version Download (12MB) | Preview |
Abstract
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.
| Item Type: | Article |
|---|---|
| Additional Information and Comments: | This is the author's version of an article that has been accepted for publication in IEEE Computer Graphics and Applications. Once published, the final version will be available online at:https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=38 |
| Faculty / Department: | Faculty of Human and Digital Sciences > Mathematics and Computer Science |
| Depositing User: | Kapil Dev |
| Date Deposited: | 23 Sep 2020 08:44 |
| Last Modified: | 23 Sep 2020 08:44 |
| URI: | https://hira.hope.ac.uk/id/eprint/3146 |
Actions (login required)
 |
View Item |
Altmetric
Altmetric
