Skip to content

yhlscut/C4

master
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 

Cascading Convolutional Color Constancy

Huanglin Yu, Ke Chen*, Kaiqi Wang, Yanlin Qian, Zhaoxiang Zhang, Kui Jia     AAAI 2020 [paper link]

This implementation uses Pytorch.

Installation

Please install Anaconda firstly.

git clone https://github.com/yhlscut/C4.git
cd C4-master
## Create python env with relevant packages
conda create --name C4 python=3.6
source activate C4
pip install -U pip
pip install -r requirements.txt
conda install pytorch torchvision cudatoolkit=9.0 -c pytorch  # cudatoolkit=10.0 for cuda10

Tested on pytorch >= 1.0 and python3.

Download

Dataset

Shi's Re-processing of Gehler's Raw Dataset:

  • Download the 4 zip files from the website and unzip them
  • Extract images in the /cs/chroma/data/canon_dataset/586_dataset/png directory into ./data/images/, without creating subfolders.
  • Masking MCC chats:
  bash ./data/run.sh

Pretrained models

  • Pretrained models can be downloaded here. To reproduce the results reported in the paper, the pretrained models(*.pth) should be placed in ./trained_models/, and then test model directly

Run code

Open the visdom service

python -m visdom.server -p 8008

Training

  • Please train the three-fold models (modify foldnum=0 to be foldnum=1 or foldnum=2 in line 6 of ./scripts/train_sq_1stage.sh and ./scripts/train_sq_3stage.sh accordingly)
  • Train the C4_sq_1stage first:
bash ./scripts/train_sq_1stage.sh
  • Train the C4_sq_3stage (Before that, please move the directory ./log/C4_sq_1stage to ./trained_models/):
bash ./scripts/train_sq_3stage.sh

Testing

  • After training, move the trained models directory in ./log/C4_sq_3stage to ./trained_models/, and run:
bash ./scripts/test_sq_3stage.sh
  • To reproduce the results reported in the paper, move the pretrained models(*.pth) downloaded from here to ./trained_models/, and then test model directly.

Citing this work

If you find this code useful for your research, please consider citing the following paper:

@inproceedings{yu2020cascading,
  title={Cascading Convolutional Color Constancy},
  author={Yu, Huanglin and Chen, Ke and Wang, Kaiqi and Qian, Yanlin and Zhang, Zhaoxiang and Jia, Kui},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  year={2020}
}

Acknowledgements

This work is supported in part by the National Natural Science Foundation of China (Grant No.: 61771201,61902131), the Program for Guangdong Introducing Innovative and Enterpreneurial Teams (Grant No.:2017ZT07X183), the Fundamental Research Funds for the Central Universities (Grant No.: D2193130), and the SCUT Program (Grant No.: D6192110).

About

The code for AAAI 2020 paper "Cascading Convolutional Color Constancy"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published