HVI-CIDNet

HVI-CIDNet restores low-light images through hue, saturation and intensity processing.

Tasks: restoration
Sizes: t at 256 px
Install: pip install libreyolo
Support tier: Inference only, since v1.6.0. Predict, validate and export only. Training features do not apply.
Upstream: HVI-CIDNet by HVI-CIDNet authors, MIT. Paper, source
Licenses: Code MIT, weights MIT. Commercial use

Install

bash

pip install "libreyolo"

Predict

Python

from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreHVICIDNett-restore.pt", device="cpu")result = model(SAMPLE_IMAGE, gamma=1.0, saturation=1.0, intensity=1.0)result.restored.save("enhanced.png")

gamma, saturation and intensity each default to 1.0. Validation uses paired image data. Training and export are not supported.

Validate

Python

from libreyolo import LibreYOLO model = LibreYOLO("LibreHVICIDNett-restore.pt", device="cpu")# Paired restoration dataset YAML: degraded images in inputs/, clean targets in targets/, matched by file stem.metrics = 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
LibreHVICIDNett-restore.pt	mit

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: HVI-CIDNet, HVI-CIDNet authors
Upstream license: MIT
Upstream source: github.com/Fediory/HVI-CIDNet
LibreYOLO code: MIT
Weights: MIT, republished at huggingface.co/LibreYOLO
Interpretation: The publisher declares MIT for the model and generalization checkpoint.

Citation

@article{yan2025hvi,
  title={HVI: A New color space for Low-light Image Enhancement},
  author={Yan, Qingsen and Feng, Yixu and Zhang, Cheng and Pang, Guansong and Shi, Kangbiao and Wu, Peng and Dong, Wei and Sun, Jinqiu and Zhang, Yanning},
  journal={arXiv preprint arXiv:2502.20272},
  year={2025}
}

Copied from the authors' citation block at raw.githubusercontent.com/Fediory/HVI-CIDNet/master/Readme.md.