Diversity Augmented Conditional Generative Adversarial Network for Enhanced Multimodal Image-to-Image Translation

no code implementations • 1 Jan 2021 • Yunlong MENG, Lin Xu

We propose Diversity Augmented conditional Generative Adversarial Network (DivAugGAN), a highly effective solution to further resolve the mode collapse problem and enhance the diversity for the generated images.

Generative Adversarial Network Image-to-Image Translation +1