HVI-CIDNet+: Beyond Extreme Darkness for Low-Light Image Enhancement

May 17, 2026 Β· View on GitHub

Β 

HVI-CIDNet+: Beyond Extreme Darkness for Low-Light Image Enhancement

Qingsen Yan, Kangbiao Shi, Yixu Feng, Tao Hu, Peng Wu, Guansong Pang

News πŸ†•

  • 2025.07.11Β Upgraded version paper as "HVI-CIDNet+: Beyond Extreme Darkness for Low-Light Image Enhancement" inΒ Arxiv. The new code, models and results will be uploaded soon. (code_link：Github) πŸ”₯

Proposed HVI-CIDNet+ βš™

HVI-CIDNet+ pipeline:

results3

Visual Comparison πŸ–Ό

LOL-v1, LOL-v2-real, and LOL-v2-synthetic:

results1

DICM, LIME, MEF, NPE, and VV:

results2

1. Get Started πŸŒ‘

Dependencies and Installation

(1) Clone Repo

git clone git@github.com:shikangbiao/CIDNet_extension.git

(2) Install Dependencies

conda env create -f HVI-CIDNet+.yaml

Data Preparation

You can refer to the following links to download the datasets.

Then, put them in the following folder:

datasets (click to expand) 
β”œβ”€β”€ datasets
	β”œβ”€β”€ DICM
	β”œβ”€β”€ LIME
	β”œβ”€β”€ LOLdataset
		β”œβ”€β”€ our485
			β”œβ”€β”€low
			β”œβ”€β”€high
		β”œβ”€β”€ eval15
			β”œβ”€β”€low
			β”œβ”€β”€high
	β”œβ”€β”€ LOLv2
		β”œβ”€β”€ Real_captured
			β”œβ”€β”€ Train
				β”œβ”€β”€ Low
				β”œβ”€β”€ Normal
			β”œβ”€β”€ Test
				β”œβ”€β”€ Low
				β”œβ”€β”€ Normal
		β”œβ”€β”€ Synthetic
			β”œβ”€β”€ Train
				β”œβ”€β”€ Low
				β”œβ”€β”€ Normal
			β”œβ”€β”€ Test
				β”œβ”€β”€ Low
				β”œβ”€β”€ Normal
	β”œβ”€β”€ MEF
	β”œβ”€β”€ NPE
	β”œβ”€β”€ SICE
		β”œβ”€β”€ Dataset
			β”œβ”€β”€ eval
				β”œβ”€β”€ target
				β”œβ”€β”€ test
			β”œβ”€β”€ label
			β”œβ”€β”€ train
				β”œβ”€β”€ 1
				β”œβ”€β”€ 2
				...
		β”œβ”€β”€ SICE_Grad
		β”œβ”€β”€ SICE_Mix
		β”œβ”€β”€ SICE_Reshape
	β”œβ”€β”€ Sony_total_dark
		β”œβ”€β”€ eval
			β”œβ”€β”€ long
			β”œβ”€β”€ short
		β”œβ”€β”€ test
			β”œβ”€β”€ long
				β”œβ”€β”€ 10003
				β”œβ”€β”€ 10006
				...
			β”œβ”€β”€ short
				β”œβ”€β”€ 10003
				β”œβ”€β”€ 10006
				...
		β”œβ”€β”€ train
			β”œβ”€β”€ long
				β”œβ”€β”€ 00001
				β”œβ”€β”€ 00002
				...
			β”œβ”€β”€ short
				β”œβ”€β”€ 00001
				β”œβ”€β”€ 00002
				...
	β”œβ”€β”€ VV

2. Testing πŸŒ’

Download our weights from [Google Drive]

  • You can test our HVI-CIDNet+ as followed, all the results will saved in ./output folder:
(click to expand) 
# LOLv1
python eval.py --lol

# LOLv2-real
python eval.py --lol_v2_real

# LOLv2-syn
python eval.py --lol_v2_syn

# SICE
python eval.py --SICE_grad # output SICE_grad
python eval.py --SICE_mix # output SICE_mix

# Sony-Total-Dark
python eval_SID.py --SID

# five unpaired datasets DICM, LIME, MEF, NPE, VV. 
# You can change "--DICM" to the other unpaired datasets "LIME, MEF, NPE, VV".
python eval.py --unpaired --DICM
  • Also, you can test all the metrics mentioned in our paper as follows:
(click to expand) 
# LOLv1
python measure.py --lol

# LOLv2-real
python measure.py --lol_v2_real

# LOLv2-syn
python measure.py --lol_v2_syn

# Sony-Total-Dark
python measure_SID.py --SID

# SICE-Grad
python measure.py --SICE_grad

# SICE-Mix
python measure.py --SICE_mix

# five unpaired datasets DICM, LIME, MEF, NPE, VV. 
# You can change "--DICM" to the other unpaired datasets "LIME, MEF, NPE, VV".
python measure_niqe_bris.py --DICM

# Note: Following LLFlow, KinD, and Retinxformer, we have also adjusted the brightness of the output image produced by the network, based on the average value of GroundTruth (GT). This only works in paired datasets. If you want to measure it, please add "--use_GT_mean".
# 
# e.g.
python measure.py --lol --use_GT_mean
  • Evaluating the Parameters, FLOPs, and running time of HVI-CIDNet+:
python net_test.py

3. Training πŸŒ“

The training code will be uploaded soon.

4. Contacts πŸŒ”

If you have any questions, please contact us or submit an issue to the repository!

Kangbiao Shi (18334840904@163.com)

5. Citation πŸŒ•

If you find our work useful for your research, please cite our paper

@article{yan2025hvi,
  title={HVI-CIDNet+: Beyond Extreme Darkness for Low-Light Image Enhancement},
  author={Yan, Qingsen and Shi, Kangbiao and Feng, Yixu and Hu, Tao and Wu, Peng and Pang, Guansong and Zhang, Yanning},
  journal={arXiv preprint arXiv:2507.06814},
  year={2025}
}

@inproceedings{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},
  booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages={5678--5687},
  year={2025}
}