# All-In-One-Underwater-Image-Enhancement-using-Domain-Adversarial-Learning

**Repository Path**: jason_way/All-In-One-Underwater-Image-Enhancement-using-Domain-Adversarial-Learning

## Basic Information

- **Project Name**: All-In-One-Underwater-Image-Enhancement-using-Domain-Adversarial-Learning
- **Description**: [CVPRW 2019] All-In-One Underwater Image Enhancement using Domain-Adversarial Learning
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 2
- **Forks**: 0
- **Created**: 2021-05-13
- **Last Updated**: 2023-04-01

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# All-In-One-Underwater-Image-Enhancement-using-Domain-Adversarial-Learning

Code for All-In-One Underwater Image Enhancement using Domain-Adversarial Learning [[paper](http://openaccess.thecvf.com/content_CVPRW_2019/html/UG2_Prize_Challenge/Uplavikar_All-in-One_Underwater_Image_Enhancement_Using_Domain-Adversarial_Learning_CVPRW_2019_paper.html)] [[arXiv](https://arxiv.org/abs/1905.13342)]

Synthesized [NYU Depth V2](https://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html) Underwater Dataset based on [Anwar et al. (2018)](https://arxiv.org/abs/1807.03528)

All the dependencies can be installed by creating a conda environment from the `environment.yml` file as follows

```conda env create --name envname -f=environments.yml```

Some parts of code adopted from https://github.com/milesial/Pytorch-UNet and https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix

If you find this work helpful and plan to use this in your project, please cite us by using the following bibtex

```
@InProceedings{Uplavikar_2019_CVPR_Workshops,
author = {M Uplavikar, Pritish and Wu, Zhenyu and Wang, Zhangyang},
title = {All-in-One Underwater Image Enhancement Using Domain-Adversarial Learning},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}
```