README.md

November 2, 2020 · View on GitHub

TensorFlow and PyTorch implementations of the paper Fast Underwater Image Enhancement for Improved Visual Perception (RA-L 2020) and other GAN-based models.

funie-fig

Resources

Training pipelines for FUnIE-GAN and UGAN (original repo) on TensorFlow (Keras) and PyTorch
Modules for image quality analysis based on UIQM, SSIM, and PSNR (see Evaluation)

Enhanced underwater imagery	Improved detection and pose estimation

FUnIE-GAN Features

Provides competitive performance for underwater image enhancement
Offers real-time inference on single-board computers
- 48+ FPS on Jetson AGX Xavier, 25+ FPS on Jetson TX2
- 148+ FPS on Nvidia GTX 1080
Suitable for underwater robotic deployments for enhanced vision

FUnIE-GAN Pointers

Paper: https://ieeexplore.ieee.org/document/9001231
Preprint: https://arxiv.org/pdf/1903.09766.pdf
Datasets: http://irvlab.cs.umn.edu/resources/euvp-dataset

Bibliography entry for citation:

@article{islam2019fast,
    title={Fast Underwater Image Enhancement for Improved Visual Perception},
    author={Islam, Md Jahidul and Xia, Youya and Sattar, Junaed},
    journal={IEEE Robotics and Automation Letters (RA-L)},
    volume={5},
    number={2},
    pages={3227--3234},
    year={2020},
    publisher={IEEE}
}

Underwater Image Enhancement: Recent Research and Resources

2019

Paper	Theme	Code	Data
Multiscale Dense-GAN	Residual multiscale dense block as generator
Fusion-GAN	FGAN-based model, loss function formulation		U45
UDAE	U-Net denoising autoencoder
VDSR	ResNet-based model, loss function formulation
JWCDN	Joint wavelength compensation and dehazing
AWMD-Cycle-GAN	Adaptive weighting for multi-discriminator training
WAug Encoder-Decoder	Encoder-decoder module with wavelet pooling and unpooling	GitHub
Water-Net	Dataset and benchmark	GitHub	UIEB

2017-18

Paper	Theme	Code	Data
UGAN	Several GAN-based models, dataset formulation	GitHub	Uw-imagenet
Underwater-GAN	Loss function formulation, cGAN-based model
LAB-MSR	Multi-scale Retinex-based framework
Water-GAN	Data generation from in-air image and depth pairings	GitHub	MHL, Field data
UIE-Net	CNN-based model for color correction and haze removal