Published: ACCV'24, Hanoi, Veitnam

LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyond (Paper)

Md Tanvir Islam ¹, Inzamamul Alam ¹, Simon S. Woo ^{1, *}, Saeed Anwar ², IK Hyun Lee ³, Khan Muhammad ^{1, *}

| 1. Sungkyunkwan University, South Korea | 2. ANU, Australia | 3. Tech University of Korea, South Korea || *Corresponding Author |

---

NEWS

• Trained weights will be uploaded soon.
• Proposed TriFuse model code is updated.
• Dataset is uploaded online.

---

Dataset Download

1. Kaggle: https://www.kaggle.com/datasets/tanvirnwu/loli-street-low-light-image-enhancement-of-street
2. Google Drive: https://drive.google.com/file/d/1xfATFqrYvMU5a4eLJ5iMi7PVts1x3mmi/view?usp=sharing

---

LoLI-Street Dataset

Proposed: TriFuse

Dependencies

pip install -r requirements.txt

How to train?

You need to modify datasets/dataset.py and configs/*.yml slightly for your environment, and then:

python train.py  

How to test?

python evaluate.py

Cite this Paper

If you find our work useful in your research, please consider citing our paper:

@InProceedings{Islam_2024_ACCV,
    author    = {Islam, Md Tanvir and Alam, Inzamamul and Woo, Simon S. and Anwar, Saeed and Lee, IK Hyun and Muhammad, Khan},
    title     = {LoLI-Street: Benchmarking Low-light Image Enhancement and Beyond},
    booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)},
    month     = {December},
    year      = {2024},
    pages     = {1250-1267}
}