# Efficient High-Resolution Image-to-Image Translation using Multi-Scale Gradient U-Net

arXiv: https://arxiv.org/abs/2105.13067 · HTML: https://mlsanity.com/paper/2105.13067/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 18 references that are in the map.
- First posted on arXiv 27 May 2021.

## Builds on (most cited first, 11 of 11)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [SPA-GAN: Spatial Attention GAN for Image-to-Image Translation](https://mlsanity.com/paper/1908.06616/) (2019)
- [Perceptual Adversarial Networks for Image-to-Image Transformation](https://mlsanity.com/paper/1706.09138/) (2017)
- [PCSGAN: Perceptual Cyclic-Synthesized Generative Adversarial Networks for Thermal and NIR to Visible Image Transformation](https://mlsanity.com/paper/2002.07082/) (2020)
- [CSGAN: Cyclic-Synthesized Generative Adversarial Networks for Image-to-Image Transformation](https://mlsanity.com/paper/1901.03554/) (2019)

## Built on by (most cited first, 3 of 3)

- [Automated 3D Tumor Segmentation using Temporal Cubic PatchGAN (TCuP-GAN)](https://mlsanity.com/paper/2311.14148/) (2023)
- [Semantic Map Injected GAN Training for Image-to-Image Translation](https://mlsanity.com/paper/2112.01845/) (2021)
- [Enhancing Underwater Images Using Deep Learning with Subjective Image Quality Integration](https://mlsanity.com/paper/2507.05393/) (2025)

## Abstract (arXiv)

Recently, Conditional Generative Adversarial Network (Conditional GAN) have shown very promising performance in several image-to-image translation applications. However, the uses of these conditional GANs are quite limited to low-resolution images, such as 256X256.The Pix2Pix-HD is a recent attempt to utilize the conditional GAN for high-resolution image synthesis. In this paper, we propose a Multi-Scale Gradient based U-Net (MSG U-Net) model for high-resolution image-to-image translation up to 2048X1024 resolution. The proposed model is trained by allowing the flow of gradients from multiple-discriminators to a single generator at multiple scales. The proposed MSG U-Net architecture leads to photo-realistic high-resolution image-to-image translation. Moreover, the proposed model is computationally efficient as com-pared to the Pix2Pix-HD with an improvement in the inference time nearly by 2.5 times. We provide the code of MSG U-Net model at https://github.com/laxmaniron/MSG-U-Net.