From Language Games to Drawing Games

Abstract

We attempt to automate various artistic processes by inventing a set of drawing games, analogous to the approach taken by emergent language research in inventing communication games. A critical difference is that drawing games demand much less effort from the receiver than do language games. Artists must work with pre-trained viewers who spend little time learning artist specific representational conventions, but who instead have a pre-trained visual system optimized for behaviour in the world by understanding to varying extents the environment's visual affordances. After considering various kinds of drawing game we present some preliminary experiments which have generated images by closing the generative-critical loop.

References in corpus (8)

• A Simple Framework for Contrastive Learning of Visual Representations
• DRAW: A Recurrent Neural Network For Image Generation
• A Neural Representation of Sketch Drawings
• Illuminating search spaces by mapping elites
• MONet: Unsupervised Scene Decomposition and Representation
• Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
• Drip Paintings and Fractal Analysis
• Unsupervised Doodling and Painting with Improved SPIRAL

Cited by in corpus (3)

• Generative Art Using Neural Visual Grammars and Dual Encoders
• Learning to Draw: Emergent Communication through Sketching
• Shared Visual Representations of Drawing for Communication: How do different biases affect human interpretability and intent?