DDColor

DDColor predicts image color from luminance.

Tasks: restoration
Install: pip install libreyolo
Support tier: Inference only, since v1.6.0. Predict, validate and export only. Training features do not apply.
Upstream: DDColor by DDColor authors, Apache-2.0. Paper, source
Licenses: Code MIT, weights Apache-2.0. Commercial use

Install

bash

pip install "libreyolo"

Predict

Python

from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreDDColort-restore.pt", device="cpu")result = model(SAMPLE_IMAGE)result.restored.save("colorized.png")

The tiny and large variants return restored color images. Validation uses paired image data. Training and export are not supported.

Validate

Python

from libreyolo import LibreYOLO model = LibreYOLO("LibreDDColort-restore.pt", device="cpu")# Restore dataset YAML pairing grayscale inputs/val with color targets/val by file stemmetrics = model.val(data="path/to/your/restore.yaml", workers=0)print(metrics)

Use the dataset format for this task. Validation explains the dataset requirements and returned metrics.

Checkpoints

File	Weights license
Restoration
LibreDDColort-restore.pt	apache-2.0
LibreDDColorl-restore.pt	apache-2.0

Every file above exists in the LibreYOLO org today and downloads on first use.

Licensing

Check the license on the Hugging Face repository of the specific weights you download. Every checkpoint in the LibreYOLO org carries one, and they are not always the same across a family. That repository is the authoritative source; the summary below describes what applied when this page was last verified.

This is a description of the licenses involved, not legal advice. If the answer matters commercially, read the licenses yourself and take your own counsel.

Original work: DDColor, DDColor authors
Upstream license: Apache-2.0
Upstream source: github.com/piddnad/DDColor
LibreYOLO code: MIT
Weights: Apache-2.0, republished at huggingface.co/LibreYOLO
Interpretation: The publisher declares Apache-2.0 for the mirrored artifacts.

Citation

@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}
}

Copied from the authors' citation block at raw.githubusercontent.com/piddnad/DDColor/master/README.md.