Repository for the paper Underwater Image Super-Resolution using Deep Residual Multipliers (ICRA 2020). Pre-print.
- Proposed dataset: USR-248
- Proposed model: SRDRM and SRDRM-GAN for underwater image super-resolution
- Models in comparison: SRGAN, ESRGAN, EDSRGAN, ResNetSR, SRCNN, and DSRCNN
- Requirements: TensorFlow >= 1.11 and Keras >= 2.2
- Download the data, setup data-paths in the training scripts
- train-GAN-nx.py: SRDRM-GAN, SRGAN, ESRGAN, EDSRGAN
- train-generative-models-nx.py: SRDRM, ResNetSR, SRCNN, DSRCNN
- Use the test-scripts for evaluating different models
- A few test images: data/test/ (ground-truth: high_res)
- Use the measure.py for quantitative analysis
@inproceedings{islam2020srdrm,
title={{Underwater Image Super-Resolution using Deep Residual Multipliers}},
author={Islam, Md Jahidul and Enan, Sadman Sakib and Luo, Peigen and Sattar, Junaed},
booktitle={IEEE International Conference on Robotics and Automation (ICRA)},
year={2020},
organization={IEEE}
}
- https://github.com/Mulns/SuperSR
- https://github.com/david-gpu/srez
- https://github.com/wandb/superres
- https://github.com/tensorlayer/srgan
- https://github.com/icpm/super-resolution
- https://github.com/alexjc/neural-enhance
- https://github.com/jiny2001/dcscn-super-resolution
- https://github.com/titu1994/Image-Super-Resolution
- https://github.com/PacktPublishing/Advanced-Deep-Learning-with-Keras