# In2I : Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1711.09334 · HTML: https://mlsanity.com/paper/1711.09334/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2017.

## Built on by (most cited first, 6 of 6)

- [MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2103.04224/) (2021)
- [UPHDR-GAN: Generative Adversarial Network for High Dynamic Range Imaging with Unpaired Data](https://mlsanity.com/paper/2102.01850/) (2021)
- [Robust pedestrian detection in thermal imagery using synthesized images](https://mlsanity.com/paper/2102.02005/) (2021)
- [Multimodal Face Synthesis from Visual Attributes](https://mlsanity.com/paper/2104.04362/) (2021)
- [I2I-Galip: Unsupervised Medical Image Translation Using Generative Adversarial CLIP](https://mlsanity.com/paper/2409.12399/) (2024)
- [Generating Thermal Human Faces for Physiological Assessment Using Thermal Sensor Auxiliary Labels](https://mlsanity.com/paper/2106.08091/) (2021)

## Abstract (arXiv)

In unsupervised image-to-image translation, the goal is to learn the mapping between an input image and an output image using a set of unpaired training images. In this paper, we propose an extension of the unsupervised image-to-image translation problem to multiple input setting. Given a set of paired images from multiple modalities, a transformation is learned to translate the input into a specified domain. For this purpose, we introduce a Generative Adversarial Network (GAN) based framework along with a multi-modal generator structure and a new loss term, latent consistency loss. Through various experiments we show that leveraging multiple inputs generally improves the visual quality of the translated images. Moreover, we show that the proposed method outperforms current state-of-the-art unsupervised image-to-image translation methods.