# Deep Automodulators

arXiv: https://arxiv.org/abs/1912.10321 · HTML: https://mlsanity.com/paper/1912.10321/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2019.

## Built on by (most cited first, 4 of 4)

- [Generative Modelling With Inverse Heat Dissipation](https://mlsanity.com/paper/2206.13397/) (2022)
- [Using latent space regression to analyze and leverage compositionality in GANs](https://mlsanity.com/paper/2103.10426/) (2021)
- [Video Autoencoder: self-supervised disentanglement of static 3D structure and motion](https://mlsanity.com/paper/2110.02951/) (2021)
- [Diverse Shape Completion via Style Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2311.11184/) (2023)

## Abstract (arXiv)

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.