Art Creation with Multi-Conditional StyleGANs

Abstract

Creating art is often viewed as a uniquely human endeavor. In this paper, we introduce a multi-conditional Generative Adversarial Network (GAN) approach trained on large amounts of human paintings to synthesize realistic-looking paintings that emulate human art. Our approach is based on the StyleGAN neural network architecture, but incorporates a custom multi-conditional control mechanism that provides fine-granular control over characteristics of the generated paintings, e.g., with regard to the perceived emotion evoked in a spectator. We also investigate several evaluation techniques tailored to multi-conditional generation.

Cite

Text

Dobler et al. "Art Creation with Multi-Conditional StyleGANs." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/684

Markdown

[Dobler et al. "Art Creation with Multi-Conditional StyleGANs." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/dobler2022ijcai-art/) doi:10.24963/IJCAI.2022/684

BibTeX

@inproceedings{dobler2022ijcai-art,
  title     = {{Art Creation with Multi-Conditional StyleGANs}},
  author    = {Dobler, Konstantin and Hübscher, Florian and Westphal, Jan and Múnera, Alejandro Sierra and de Melo, Gerard and Krestel, Ralf},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {4936-4942},
  doi       = {10.24963/IJCAI.2022/684},
  url       = {https://mlanthology.org/ijcai/2022/dobler2022ijcai-art/}
}