The preparation for the pre-trained model. (a) Randomly select template A from the template pool (underwater domain). Then, the Color Transfer module, guided by template A, degrades an in-air natural image from INaturalist into underwater domain, constructing paired datasets for training image-to-image diffusion model. (b) The image-to-image diffusion model SR3 is trained to learn the prior knowledge, the mapping from the real underwater degradation domain and the real in-air natural domain, and to generate the corresponding enhancement results under the condition of the input synthetic underwater images produced by Color Transfer. |
- Pytorch >= 1.13.1
- CUDA >= 11.3
- Other required packages in
requirements.txt
| Name | Model |
|---|---|
| CLIP-UIE | Download 🔗 |
| Learned Prompt | Download 🔗 |
- Putting your data into the dataset folder.
- Download the pre-trained model. Then, put the model in the experiments_supervised folder and change the corresponding paths in config/sr_sr3_32_256_UIEB_SUIM_E_plus_finetune_clip_classifier.json.
- Execute infer_finetune_infer.py to get the inference results in a new folder called experiments.
- More details will be released after the article is accepted.
Our code is based on SR3 and CLIP-LIT. You can refer to their README files and source code for more implementation details.
If you find our work useful for your research, please consider citing the paper: