Skip to content
/ P2CNet Public

Deep Color Compensation for Generalized Underwater Image Enhancement

Notifications You must be signed in to change notification settings

Ray2OUC/P2CNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

33 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Deep Color Compensation for Generalized Underwater Image Enhancement [T-CSVT 2024]

Demo and Implementation of P2CNet and two-stage UIE (An free lunch for most existing UIE models without any tuning):

P2CNet

Our approach can successfully break through the generalization bottleneck of current deep UIE models without re-training:

Deep

Our approach can also benefit DCP-based methods by effective dark channel extraction:

DCP

Our work was published on IEEE Transactions on Circuits and Systems for Video Technology 2024, and can be accessed via manuscript.

Probabilistic Color Compensation Network Architecture

Our P2CNet estimates the probabilistic distribution of colors by multi-scale volumetric fusion of texture and color features.

P2CNet

Pre-Trained Weights

The P2CNet network and model weights are provided in the models and ckpt files respectively.

For the enhancement network and the model weights of CLUIE, please refer to the CLUIE-Net

DEMO:P2CNet+CLUIE-Net

We provide the enhancement demo of using P2CNet and CLUIE-Net in demo.ipynb and test.py, which are easily to be adapted with most existing enhancement models or algorthms.

Train:P2CNet

We provide the cleaned code for training P2CNet in train.py, please read the annotations in this code file. Here are some helpful tips for training P2CNet:

  1. Preparing workspace.
  2. Preparing pre-resized SUIM-E data in train_path (320x320 in our experiments) and test_path (256x256).
  3. You may add some metrics (for example the UIQM) for the test phase to see what happens during the training.

Citation

If you are interested in this work, please cite the following work:

@ARTICLE{10220126,
  author={Rao, Yuan and Liu, Wenjie and Li, Kunqian and Fan, Hao and Wang, Sen and Dong, Junyu},
  journal={IEEE Transactions on Circuits and Systems for Video Technology}, 
  title={Deep Color Compensation for Generalized Underwater Image Enhancement}, 
  year={2024},
  volume={34},
  number={4},
  pages={2577-2590},
  doi={10.1109/TCSVT.2023.3305777}}

About

Deep Color Compensation for Generalized Underwater Image Enhancement

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published