Neural Color Operators for Sequential Image Retouching (Pytorch Implementation)

Yili Wang, Xin Li, Kun Xu, Dongliang He, Qi Zhang, Fu Li, Errui Ding

[arXiv] [project] [doi]

Get Started

• Clone this repo

  git clone https://github.com/amberwangyili/neurop-pytorch
  

• Download the Dataset from 百度网盘 (code:jvvq) and unzip in project folder

  tree -L 2 neurop-pytorch/datasets
  # the output should be like the following:
  datasets/
  ├── dataset-dark
  │   ├── testA
  │   ├── testB
  │   ├── trainA
  │   └── trainB
  ├── dataset-init
  │   ├── BC
  │   ├── EX
  │   └── VB
  ├── dataset-lite
  │   ├── testA
  │   ├── testB
  │   ├── trainA
  │   └── trainB
  └── dataset-ppr
      ├── ppr-a
      ├── ppr-b
      ├── ppr-c
      ├── testA
      ├── testM
      ├── trainA
      └── trainM

• Install Dependencies

  cd neurop-pytorch/codes
  pip install -r requirements.txt 

Test

1. We provide pretrained model weights for MIT-Adobe FiveK and PPR10K in neurop-pytorch/pretrain_models/

2. Run command:

   python test.py -config configs/test/<configuaration-name>.yaml 

3. The evaluation results will be in the neurop-pytorch/results folder

Train

1. Initialization individual neural color operators:

   python train.py -config ./configs/init_neurop.yaml 

2. Finetune with strength predictors:

   python train.py -config ./configs/train/<configuration-name>.yaml