GAN 2.0: NVIDIA’s Hyperrealistic Face Generator | Synced

The NVIDIA paper proposes an alternative generator architecture for GAN that draws insights from style transfer techniques. The system can learn and separate different aspects of an image unsupervi...

By · · 1 min read

Source: Synced | AI Technology & Industry Review

The NVIDIA paper proposes an alternative generator architecture for GAN that draws insights from style transfer techniques. The system can learn and separate different aspects of an image unsupervised; and enables intuitive, scale-specific control of the synthesis.