Shallow Art: Art Extension Through Simple Machine Learning
This work addresses art generation for computational creativity, but it is incremental as it applies existing methods to new data without major innovations.
The paper tackled the problem of art generation by training simple classification and regression models on datasets of computer-generated images and artworks from van Gogh and Rembrandt, then using them to complete missing halves of images, with results displayed and implications for computational creativity explored.
Shallow Art presents, implements, and tests the use of simple single-output classification and regression models for the purpose of art generation. Various machine learning algorithms are trained on collections of computer generated images, artworks from Vincent van Gogh, and artworks from Rembrandt van Rijn. These models are then provided half of an image and asked to complete the missing side. The resulting images are displayed, and we explore implications for computational creativity.