December 2022
Volume 22, Issue 14
Open Access
Vision Sciences Society Annual Meeting Abstract  |   December 2022
Perceptual Exploration of Latent Space for Pictorial Composition
Author Affiliations & Notes
  • Pierre Lelièvre
    Laboratoire des systèmes perceptifs, Département d’études cognitives, École normale supérieure, PSL University, CNRS, 75005 Paris, France
    Science Arts Création Recherche (EA 7410), École normale supérieure, PSL University, CNRS, 75005 Paris, France
  • Peter Neri
    Laboratoire des systèmes perceptifs, Département d’études cognitives, École normale supérieure, PSL University, CNRS, 75005 Paris, France
  • Footnotes
    Acknowledgements  Supported by grants ANR-16-CE28-0016, ANR-17-EURE-0017, ANR-10-LABX-0087 IEC and ANR-10-IDEX-0001-02 PSL from Agence Nationale de la Recherche.
Journal of Vision December 2022, Vol.22, 3287. doi:https://doi.org/10.1167/jov.22.14.3287
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Pierre Lelièvre, Peter Neri; Perceptual Exploration of Latent Space for Pictorial Composition. Journal of Vision 2022;22(14):3287. https://doi.org/10.1167/jov.22.14.3287.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Pictorial composition (the structural organization of graphical elements) is typically characterized by qualitative rules and heuristics; although informative, these tools do not support quantitative measures of global similarity/interaction of its constituent elements. The sequential non-stationary nature of the compositional process, together with the complex and evolving definition of its underlying functional units, coalesce into a perceptual phenomenon that cannot be readily modeled through pixel-based approaches such as CNNs. We adopt a different strategy, constructed around a parametric definition of stroke execution and two hierarchically nested RNN-VAE, enabling our network to tackle art material by aligning its behavior to the artistic gesture. More specifically, this network architecture extracts compositional regularities by compressing inputs to a reduced number of independent dimensions; within this framework, visual stimuli project to a continuous space that permits quantitative investigation of relevant perceptual mechanisms. Our neural network is trained on >5k small abstract vectorial compositions created by the first author over years of compositional efforts. Although this dataset is large for a single artist, its scale remains relatively small for training large networks. We address this issue by introducing constraints that support a compact representation that is both cohesive and expressive at the same time. We then study the smoothness and continuity of the resulting latent space by measuring the perceptual scale of sample similarities generated by human participants. To avoid the curse of dimensionality, we restricted exploration to circular slices of a hypersphere by extending MLDS methods to cyclic 'physical' spaces. To leverage the number of trials per participants, we demonstrate that adequate empirical exploration can be restricted to local pairs of normal triplet comparisons. Our approach serves to validate a novel modeling framework for pictorial composition, alongside psychophysical tools for measuring the quality of its representation and associated metrics.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×