Logo Generation Using Regional Features: A Faster R-CNN Approach to Generative Adversarial Networks
It addresses logo design for creative industries, but is incremental as it adapts existing methods to a specific domain.
The paper tackles logo generation by proposing LL-GAN, which uses regional features from Faster R-CNN, and achieves an Inception Score of 5.29 and Frechet Inception Distance of 223.94, outperforming StyleGAN2 and Self-Attention GAN.
In this paper we introduce Local Logo Generative Adversarial Network (LL-GAN) that uses regional features extracted from Faster R-CNN for logo generation. We demonstrate the strength of this approach by training the framework on a small style-rich dataset of real heavy metal logos to generate new ones. LL-GAN achieves Inception Score of 5.29 and Frechet Inception Distance of 223.94, improving on state-of-the-art models StyleGAN2 and Self-Attention GAN.