# Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer

arXiv: https://arxiv.org/abs/2001.05017 · HTML: https://mlsanity.com/paper/2001.05017/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2020.

## Built on by (most cited first, 15 of 15)

- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Image-to-image Translation via Hierarchical Style Disentanglement](https://mlsanity.com/paper/2103.01456/) (2021)
- [Using latent space regression to analyze and leverage compositionality in GANs](https://mlsanity.com/paper/2103.10426/) (2021)
- [Underwater Light Field Retention : Neural Rendering for Underwater Imaging](https://mlsanity.com/paper/2203.11006/) (2022)
- [End-to-End Visual Editing with a Generatively Pre-Trained Artist](https://mlsanity.com/paper/2205.01668/) (2022)
- [VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts](https://mlsanity.com/paper/2103.07292/) (2021)
- [DisUnknown: Distilling Unknown Factors for Disentanglement Learning](https://mlsanity.com/paper/2109.08090/) (2021)
- [GlassesGAN: Eyewear Personalization using Synthetic Appearance Discovery and Targeted Subspace Modeling](https://mlsanity.com/paper/2210.14145/) (2022)
- [JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting](https://mlsanity.com/paper/2106.09679/) (2021)
- [Language-free Compositional Action Generation via Decoupling Refinement](https://mlsanity.com/paper/2307.03538/) (2023)
- [Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing](https://mlsanity.com/paper/2110.11159/) (2021)
- [Object Pursuit: Building a Space of Objects via Discriminative Weight Generation](https://mlsanity.com/paper/2112.07954/) (2021)
- [Reliable Federated Disentangling Network for Non-IID Domain Feature](https://mlsanity.com/paper/2301.12798/) (2023)
- [Jurassic World Remake: Bringing Ancient Fossils Back to Life via Zero-Shot Long Image-to-Image Translation](https://mlsanity.com/paper/2308.07316/) (2023)
- [Image Denoising via Style Disentanglement](https://mlsanity.com/paper/2309.14755/) (2023)

## Abstract (arXiv)

We study the problem of learning to map, in an unsupervised way, between domains A and B, such that the samples b in B contain all the information that exists in samples a in A and some additional information. For example, ignoring occlusions, B can be people with glasses, A people without, and the glasses, would be the added information. When mapping a sample a from the first domain to the other domain, the missing information is replicated from an independent reference sample b in B. Thus, in the above example, we can create, for every person without glasses a version with the glasses observed in any face image. Our solution employs a single two-pathway encoder and a single decoder for both domains. The common part of the two domains and the separate part are encoded as two vectors, and the separate part is fixed at zero for domain A. The loss terms are minimal and involve reconstruction losses for the two domains and a domain confusion term. Our analysis shows that under mild assumptions, this architecture, which is much simpler than the literature guided-translation methods, is enough to ensure disentanglement between the two domains. We present convincing results in a few visual domains, such as no-glasses to glasses, adding facial hair based on a reference image, etc.