LYT-NET: Lightweight YUV Transformer-based Network for Low-light Image Enhancement
This addresses image quality issues in low-light conditions for applications like photography and surveillance, representing an incremental improvement with novel blocks.
The paper tackles low-light image enhancement by proposing LYT-Net, a lightweight transformer-based model that uses a dual-path approach for YUV channels, achieving state-of-the-art performance on established datasets despite low complexity.
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 https://github.com/albrateanu/LYT-Net