Timezone: »

Deep Automodulators
Ari Heljakka · Yuxin Hou · Juho Kannala · Arno Solin

Tue Dec 08 09:00 PM -- 11:00 PM (PST) @ Poster Session 2 #694

We introduce a new category of generative autoencoders called automodulators. These networks can faithfully reproduce individual real-world input images like regular autoencoders, but also generate a fused sample from an arbitrary combination of several such images, allowing instantaneous "style-mixing" and other new applications. An automodulator decouples the data flow of decoder operations from statistical properties thereof and uses the latent vector to modulate the former by the latter, with a principled approach for mutual disentanglement of decoder layers. Prior work has explored similar decoder architecture with GANs, but their focus has been on random sampling. A corresponding autoencoder could operate on real input images. For the first time, we show how to train such a general-purpose model with sharp outputs in high resolution, using novel training techniques, demonstrated on four image data sets. Besides style-mixing, we show state-of-the-art results in autoencoder comparison, and visual image quality nearly indistinguishable from state-of-the-art GANs. We expect the automodulator variants to become a useful building block for image applications and other data domains.

Author Information

Ari Heljakka (Aalto University)
Yuxin Hou (Aalto University)
Juho Kannala (Aalto University)
Arno Solin (Aalto University)

More from the Same Authors