# Mask Based Unsupervised Content Transfer

arXiv: https://arxiv.org/abs/1906.06558 · HTML: https://mlsanity.com/paper/1906.06558/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2019.

## Built on by (most cited first, 8 of 8)

- [Stitch it in Time: GAN-Based Facial Editing of Real Videos](https://mlsanity.com/paper/2201.08361/) (2022)
- [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)
- [State-of-the-Art in the Architecture, Methods and Applications of StyleGAN](https://mlsanity.com/paper/2202.14020/) (2022)
- [FEAT: Face Editing with Attention](https://mlsanity.com/paper/2202.02713/) (2022)
- [Defect Transfer GAN: Diverse Defect Synthesis for Data Augmentation](https://mlsanity.com/paper/2302.08366/) (2023)
- [End-to-End Visual Editing with a Generatively Pre-Trained Artist](https://mlsanity.com/paper/2205.01668/) (2022)
- [JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting](https://mlsanity.com/paper/2106.09679/) (2021)

## Abstract (arXiv)

We consider the problem of translating, in an unsupervised manner, between two domains where one contains some additional information compared to the other. The proposed method disentangles the common and separate parts of these domains and, through the generation of a mask, focuses the attention of the underlying network to the desired augmentation alone, without wastefully reconstructing the entire target. This enables state-of-the-art quality and variety of content translation, as demonstrated through extensive quantitative and qualitative evaluation. Our method is also capable of adding the separate content of different guide images and domains as well as remove existing separate content. Furthermore, our method enables weakly-supervised semantic segmentation of the separate part of each domain, where only class labels are provided. Our code is publicly available at https://github.com/rmokady/mbu-content-tansfer.