Emergence of Painting Ability via Recognition-Driven Evolution
This work addresses the challenge of enhancing visual communication efficiency for applications in art generation and image compression, though it appears incremental in its approach.
The paper tackled the problem of simulating the evolution of painting ability by optimizing strokes and colors to maximize recognition accuracy with minimal resources, achieving superior performance in high-level recognition tasks and showing promise as an efficient image compression technique.
From Paleolithic cave paintings to Impressionism, human painting has evolved to depict increasingly complex and detailed scenes, conveying more nuanced messages. This paper attempts to emerge this artistic capability by simulating the evolutionary pressures that enhance visual communication efficiency. Specifically, we present a model with a stroke branch and a palette branch that together simulate human-like painting. The palette branch learns a limited colour palette, while the stroke branch parameterises each stroke using Bézier curves to render an image, subsequently evaluated by a high-level recognition module. We quantify the efficiency of visual communication by measuring the recognition accuracy achieved with machine vision. The model then optimises the control points and colour choices for each stroke to maximise recognition accuracy with minimal strokes and colours. Experimental results show that our model achieves superior performance in high-level recognition tasks, delivering artistic expression and aesthetic appeal, especially in abstract sketches. Additionally, our approach shows promise as an efficient bit-level image compression technique, outperforming traditional methods.