← Search

Erik Härkönen

2 accepted papers

2021

Alias-Free Generative Adversarial Networks

NeurIPS 2021oral

We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner. This manifests itself as, e.g., detail appearing to be glued to image coordinates instead of the surfaces of…

2020

GANSpace: Discovering Interpretable GAN Controls

NeurIPS 2020poster

This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis, such as change of viewpoint, aging, lighting, and time of day. We identify important latent directions based on Principal Component Analysis (PCA) applied…