5 papers
Deep Automodulators
Ari Heljakka, Yuxin Hou, Juho Kannala +1
We introduce a new category of generative autoencoders called automodulators. These networks can faithfully reproduce individual real-world input images like regular autoencoders,…
Gaussian Process Priors for View-Aware Inference
Yuxin Hou, Ari Heljakka, Arno Solin
While frame-independent predictions with deep neural networks have become the prominent solutions to many computer vision tasks, the potential benefits of utilizing correlations be…
Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders
Ari Heljakka, Arno Solin, Juho Kannala
We present a generative autoencoder that provides fast encoding, faithful reconstructions (eg. retaining the identity of a face), sharp generated/reconstructed samples in high reso…
Pioneer Networks: Progressively Growing Generative Autoencoder
Ari Heljakka, Arno Solin, Juho Kannala
We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from th…
Recursive Chaining of Reversible Image-to-image Translators For Face Aging
Ari Heljakka, Arno Solin, Juho Kannala
This paper addresses the modeling and simulation of progressive changes over time, such as human face aging. By treating the age phases as a sequence of image domains, we construct…