/DDColor

[ICCV 2023] Official implementation of "DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders"

Primary LanguagePythonApache License 2.0Apache-2.0

🎨 DDColor

Official PyTorch implementation of ICCV 2023 Paper "DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders".

arXiv HuggingFace ModelScope demo visitors

Xiaoyang Kang, Tao Yang, Wenqi Ouyang, Peiran Ren, Lingzhi Li, Xuansong Xie

DAMO Academy, Alibaba Group

🪄 DDColor can provide vivid and natural colorization for historical black and white old photos.

🎲 It can even colorize/recolor landscapes from anime games, transforming your animated scenery into a realistic real-life style! (Image source: Genshin Impact)

🔥 News

  • [2023-12-13] Release the DDColor-tiny pre-trained model!

  • [2023-09-07] Add the Model Zoo and release three pretrained models!

  • [2023-05-15] Code release for training and inference!

  • [2023-05-05] The online demo is available!

Online Demo

We provide online demo via ModelScope. Feel free to try it out!

Methods

In short: DDColor uses multi-scale visual features to optimize learnable color tokens (i.e. color queries) and achieves state-of-the-art performance on automatic image colorization.

Installation

Requirements

  • Python >= 3.7
  • PyTorch >= 1.7

Install with conda (Recommend)

conda create -n ddcolor python=3.8
conda activate ddcolor
pip install torch==1.7.1+cu110 torchvision==0.8.2+cu110 torchaudio==0.7.2 -f https://download.pytorch.org/whl/torch_stable.html
pip install -r requirements.txt

python3 setup.py develop  # install basicsr

Quick Start

Inference with modelscope library

  1. Install modelscope:
pip install "modelscope[cv]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
  1. Run the following codes:
import cv2
from modelscope.outputs import OutputKeys
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

img_colorization = pipeline(Tasks.image_colorization, model='damo/cv_ddcolor_image-colorization')
result = img_colorization('https://modelscope.oss-cn-beijing.aliyuncs.com/test/images/audrey_hepburn.jpg')
cv2.imwrite('result.png', result[OutputKeys.OUTPUT_IMG])

It will automatically download the DDColor models.

You can find the model file pytorch_model.pt in the local path ~/.cache/modelscope/hub/damo.

Inference from local script

  1. Download the pretrained model file by simply running:
from modelscope.hub.snapshot_download import snapshot_download

model_dir = snapshot_download('damo/cv_ddcolor_image-colorization', cache_dir='./modelscope')
print('model assets saved to %s'%model_dir)

then the weights will be modelscope/damo/cv_ddcolor_image-colorization/pytorch_model.pt.

Or, download the model from Hugging Face.

  1. Run
sh scripts/inference.sh

Model Zoo

We provide several different versions of pretrained models, please check out Model Zoo.

Train

  1. Dataset preparation: download ImageNet dataset, or prepare any custom dataset of your own. Use the following script to get the dataset list file:
python data_list/get_meta_file.py
  1. Download pretrained weights for ConvNeXt and InceptionV3 and put it into pretrain folder.

  2. Specify 'meta_info_file' and other options in options/train/train_ddcolor.yml.

  3. Run

sh scripts/train.sh

Citation

If our work is helpful for your research, please consider citing:

@inproceedings{kang2023ddcolor,
  title={DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders},
  author={Kang, Xiaoyang and Yang, Tao and Ouyang, Wenqi and Ren, Peiran and Li, Lingzhi and Xie, Xuansong},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={328--338},
  year={2023}
}

Acknowledgments

We thank the authors of BasicSR for the awesome training pipeline.

Xintao Wang, Ke Yu, Kelvin C.K. Chan, Chao Dong and Chen Change Loy. BasicSR: Open Source Image and Video Restoration Toolbox. https://github.com/xinntao/BasicSR, 2020.

Some codes are adapted from ColorFormer, BigColor, ConvNeXt, Mask2Former, and DETR. Thanks for their excellent work!