Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ScribGen: Generating Scribble Art Through Metaheuristics

Soumyaratna Debnath, Ashish Tiwari, Shanmuganathan Raman

TL;DR

This work extensively analyse various metaheuristic algorithms, demonstrating their optimal balance between creativity and computational efficiency and offering better adaptability and accuracy than state-of-the-art deep generative models for image-to-scribble generation.

Abstract

Art has long been a medium for individuals to engage with the world. Scribble art, a form of abstract visual expression, features spontaneous, gestural strokes made with pens or brushes. These dynamic and expressive compositions, created quickly and impulsively, reveal intricate patterns and hidden meanings upon closer inspection. While scribble art is often associated with spontaneous expression and experimentation, it can also be planned and intentional. Some artists use scribble techniques as a starting point for their creative process, exploring the possibilities of line, shape, and texture before refining their work into more polished compositions. From ancient cave paintings to modern abstract sketches and doodles, scribble art has evolved with civilizations, reflecting diverse artistic movements and cultural influences. This evolution highlights its universal appeal, transcending language and cultural barriers and connecting people through the shared experience of creating art.

ScribGen: Generating Scribble Art Through Metaheuristics

TL;DR

This work extensively analyse various metaheuristic algorithms, demonstrating their optimal balance between creativity and computational efficiency and offering better adaptability and accuracy than state-of-the-art deep generative models for image-to-scribble generation.

Abstract

Art has long been a medium for individuals to engage with the world. Scribble art, a form of abstract visual expression, features spontaneous, gestural strokes made with pens or brushes. These dynamic and expressive compositions, created quickly and impulsively, reveal intricate patterns and hidden meanings upon closer inspection. While scribble art is often associated with spontaneous expression and experimentation, it can also be planned and intentional. Some artists use scribble techniques as a starting point for their creative process, exploring the possibilities of line, shape, and texture before refining their work into more polished compositions. From ancient cave paintings to modern abstract sketches and doodles, scribble art has evolved with civilizations, reflecting diverse artistic movements and cultural influences. This evolution highlights its universal appeal, transcending language and cultural barriers and connecting people through the shared experience of creating art.

Paper Structure

This paper contains 12 sections, 9 figures, 1 algorithm.

Table of Contents

  1. Introduction and Background
  2. Scribble Art
  3. Art and Technology
  4. Contribution
  5. Metaheuristics
  6. Scribble Art Generation as an Optimization Problem
  7. Methodology
  8. Results: Images to Scribbles
  9. Single Continuous vs Composite Generation
  10. Comparison with Deep Generative Networks
  11. Applications
  12. Conclusion

Figures (9)

  • Figure 1: Categories of Metaheuristic algorithms
  • Figure 2: Computing solution fitness and generating scribble art. Eiffel tower image generated by DALL-E 3 betker2023improving from text prompts.
  • Figure 3: Generation-wise scribbling results using different metaheuristic backbones.
  • Figure 4: Scribbles generated through different metaheuristic backbones after 2000 iterations. Input images generated by DALL-E 3 betker2023improving from text prompts.
  • Figure 5: (Top row) Convergence curves and (Bottom row) Structural Similarity index.
  • ...and 4 more figures