Gerard De Melo, Konstantin Dobler, Florian Übscher, Jan Westphal, Alejandro Sierra-M Únera, Ralf Krestel
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2202.11777")
get_code_for_paper("2202.11777")
have("2202.11777")
Connect an agent — have() is free.