CompAesth 14: Workshop on Computational Aesthetics

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/15016

Browse

Browsing CompAesth 14: Workshop on Computational Aesthetics by Subject "aesthetics"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Collaborative filtering of color aesthetics
    (ACM, 2014) O'Donovan, Peter; Agarwala, Aseem; Hertzmann, Aaron; Paul Rosin
    This paper investigates individual variation in aesthetic preferences, and learns models for predicting the preferences of individual users. Preferences for color aesthetics are learned using a collaborative filtering approach on a large dataset of rated color themes/palettes. To make predictions, matrix factorization is used to estimate latent vectors for users and color themes. We also propose two extensions to the probabilistic matrix factorization framework. We first describe a feature-based model using learned transformations from feature vectors to a latent space, then extend this model to non-linear transformations using a neural network. These extensions allow our model to predict preferences for color themes not present in the training set. We find that our approach for modelling user preferences outperforms an average aesthetic model which ignores personal variation. We also use the model for measuring theme similarity and visualizing the space of color themes.
  • Thumbnail Image
    Item
    A study of image colourfulness
    (ACM, 2014) Amati, Cristina; Mitra, Niloy J.; Weyrich, Tim; Paul Rosin
    Colourfulness is often thought of as a mere measure of quantity of colour, but user studies suggest that there are more factors influencing the perception of colourfulness. Boosting and enhancing colours are operations often performed for improving image aesthetics, but the relationship between colourfulness and aesthetics has not been thoroughly explored. By gathering perceptual data from a largescale user study we have shown how existing colourfulness metrics relate to it and that there is no direct linear dependence between colourfulness and aesthetics but correlations arise for different image categories such as: “landscape”, “abstract” or “macro”.