Corpus ID: 222141725

From Language Games to Drawing Games

  title={From Language Games to Drawing Games},
  author={Chrisantha Fernando and Daria Zenkova and Stanislav Nikolov and Simon Osindero},
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… Expand

Figures from this paper

Generative Art Using Neural Visual Grammars and Dual Encoders
A novel algorithm for producing generative art is described which allows a user to input a text string, and which in a creative response to this string, outputs an image which interprets that string. Expand


Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
It is found that the degree of structure found in the input data affects the nature of the emerged protocols, and thereby corroborate the hypothesis that structured compositional language is most likely to emerge when agents perceive the world as being structured. Expand
Unsupervised Doodling and Painting with Improved SPIRAL
It is found that when sufficiently constrained, generative agents can learn to produce images with a degree of visual abstraction, despite having only ever seen real photographs (no human brush strokes), and given enough time with the painting environment, they can produced images with considerable realism. Expand
Graphical convention formation during visual communication
Drawing is a versatile technique for visual communication, ranging from photorealistic renderings to schematic diagrams consisting entirely of symbols. How does a medium spanning such a broad rangeExpand
Visual Thinking
A visual note-taking style doesn’t only work for visual learners, but can also benefit people with different learning styles, so you can reach your full potential by tapping into your preferred learning style. Expand
DRAW: A Recurrent Neural Network For Image Generation
The Deep Recurrent Attentive Writer neural network architecture for image generation substantially improves on the state of the art for generative models on MNIST, and, when trained on the Street View House Numbers dataset, it generates images that cannot be distinguished from real data with the naked eye. Expand
Playing to the Gallery: Helping Contemporary Art in Its Struggle to Be Understood
"I have never read such a stimulating short guide to art. It should be issued as a set text in every school." (Lynn Barber, Sunday Times Now). Grayson Perry is a fully paid-up member of the artExpand
Visual order : the nature and development of pictorial representation
List of contributors Preface Introduction N. H. Freeman and M. V. Cox 1. How meaning covers the traces Alan Costall Commentary N. H. Freeman and M. V. Cox 2. A perspective on traditional artisticExpand
A Neural Representation of Sketch Drawings
We present sketch-rnn, a recurrent neural network (RNN) able to construct stroke-based drawings of common objects. The model is trained on thousands of crude human-drawn images representing hundredsExpand
An Investigation of Algorithmic Aesthetics
The main result of the work is the development of a formalism, an aesthetic system, for the algorithmic specification of aesthetic viewpoints, which is applied to six pictures shown in the paper. Expand
Vector-based navigation using grid-like representations in artificial agents
These findings show that emergent grid-like representations furnish agents with a Euclidean spatial metric and associated vector operations, providing a foundation for proficient navigation, and support neuroscientific theories that see grid cells as critical for vector-based navigation. Expand