# S-Flow GAN

## TL;DR

This paper introduces S-Flow GAN, a conditional GAN architecture that translates semantic label maps and CG edge maps into photo-realistic images, with extensions for video generation, enhancing realism and temporal coherence.

## Contribution

The paper presents a novel GAN architecture for domain translation from semantic and edge maps to realistic images, including a new video extension for temporal coherence.

## Key findings

- Effective translation from semantic maps to realistic images.
- Enhanced photo-realism in generated images.
- Temporal coherence in video generation achieved.

## Abstract

Our work offers a new method for domain translation from semantic label maps and Computer Graphic (CG) simulation edge map images to photo-realistic images. We train a Generative Adversarial Network (GAN) in a conditional way to generate a photo-realistic version of a given CG scene. Existing architectures of GANs still lack the photo-realism capabilities needed to train DNNs for computer vision tasks, we address this issue by embedding edge maps, and training it in an adversarial mode. We also offer an extension to our model that uses our GAN architecture to create visually appealing and temporally coherent videos.