Hugging Face's logo

albrateanu
/
LYT-Net

Image-to-Image
low-light
low-light-image-enhancement
image-enhancement
image-restoration
computer-vision
low-light-enhance
Eval Results
Model card Files
xet
Community
LYT-Net / README.md
albrateanu's picture
albrateanu
Update README.md
2ffeec1 verified
preview code
|
raw
history blame contribute delete
4.19 kB
metadata
license: mit
tags:
  - low-light
  - low-light-image-enhancement
  - image-enhancement
  - image-restoration
  - computer-vision
  - low-light-enhance
  - image-to-image
model-index:
  - name: LYT-Net
    results:
      - task:
          type: low-light-image-enhancement
        dataset:
          name: LOL-v1
          type: LOL-v1
        metrics:
          - name: PSNR
            type: PSNR
            value: 27.23
          - name: SSIM
            type: SSIM
            value: 0.853
      - task:
          type: low-light-image-enhancement
        dataset:
          name: LOL-v2-Real
          type: LOL-v2-Real
        metrics:
          - name: PSNR
            type: PSNR
            value: 28.41
          - name: SSIM
            type: SSIM
            value: 0.878
      - task:
          type: low-light-image-enhancement
        dataset:
          name: LOL-v2-Synthetic
          type: LOL-v2-Synthetic
        metrics:
          - name: PSNR
            type: PSNR
            value: 29.39
          - name: SSIM
            type: SSIM
            value: 0.939

[SPL 2025] LYT-Net: Lightweight YUV Transformer-based Network for Low-Light Image Enhancement

Alexandru Brateanu, Raul Balmez, Adrian Avram, Ciprian Orhei, Cosmin Ancuti

arXiv IEEE

Ranked #1 on FLOPS(G) (3.49 GFLOPS) and Params(M) (0.045M = 45k Params)

Abstract

This letter introduces LYT-Net, a novel lightweight transformer-based model for low-light image enhancement (LLIE). LYT-Net consists of several layers and detachable blocks, including our novel blocks--Channel-Wise Denoiser (CWD) and Multi-Stage Squeeze & Excite Fusion (MSEF)--along with the traditional Transformer block, Multi-Headed Self-Attention (MHSA). In our method we adopt a dual-path approach, treating chrominance channels U and V and luminance channel Y as separate entities to help the model better handle illumination adjustment and corruption restoration. Our comprehensive evaluation on established LLIE datasets demonstrates that, despite its low complexity, our model outperforms recent LLIE methods. The source code and pre-trained models are available at this https URL.

🆕 Updates

  • 27.07.2025 🤗 LYT-Net now has a new HuggingFace page! Check it out here! HF Demo coming soon!
  • 09.05.2025 📢 Check out our other works on Low-light Image Enhancement and Image Denoising!
  • 21.04.2025 📝 LYT-Net is published as a IEEE Signal Processing Letters paper. Link to paper.
  • 17.07.2024 🧪 Released rudimentary PyTorch implementation.
  • 03.04.2024 🔧 Training code re-added and adjusted.
  • 30.01.2024 📄 arXiv pre-print available.
  • 10.01.2024 🚀 Pre-trained model weights and code for training and testing are released.

🧪 Experiment

Please check the GitHub for PyTorch and TensorFlow implementations.

📚 Citation 

@article{brateanu2025lyt,
  author={Brateanu, Alexandru and Balmez, Raul and Avram, Adrian and Orhei, Ciprian and Ancuti, Cosmin},
  journal={IEEE Signal Processing Letters}, 
  title={LYT-NET: Lightweight YUV Transformer-based Network for Low-light Image Enhancement}, 
  year={2025},
  volume={},
  number={},
  pages={1-5},
  doi={10.1109/LSP.2025.3563125}}


@article{brateanu2024lyt,
  title={LYT-Net: Lightweight YUV Transformer-based Network for Low-Light Image Enhancement},
  author={Brateanu, Alexandru and Balmez, Raul and Avram, Adrian and Orhei, Ciprian and Cosmin, Ancuti},
  journal={arXiv preprint arXiv:2401.15204},
  year={2024}
}

Paper: arxiv.org/abs/2401.15204 Code: https://github.com/albrateanu/LYT-Net