LYT-NET: Lightweight YUV Transformer-Based Network for Low-Light Image Enhancement

This letter introduces LYT-Net, a novel lightweight transformer-based model for low-light image enhancement. LYT-Net consists of several layers and detachable blocks, including our novel blocks-Channel-Wise Denoiser (<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CWD</b>) and Multi-Stage Squeeze & Excite Fusion (<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MSEF</b>)-along with the traditional Transformer block, Multi-Headed Self-Attention (<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MHSA</b>). In our method we adopt a dual-path approach, treating chrominance channels <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ U$</tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ V$</tex-math></inline-formula> and luminance channel <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ Y$</tex-math></inline-formula> 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 <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/albrateanu/LYT-Net</uri>