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

2024-01-26

IEEE Signal Processing Letters

AI Summary

For low-light image enhancement (LLIE), this paper proposes a lightweight dual-path Transformer network operating in the YUV color space. It is the first to decouple luminance (Y) and chrominance (U/V) channels within YUV, enabling separate optimization of illumination adjustment and noise/artifact restoration. The method introduces a channel-wise denoising (CWD) module and a multi-stage Squeeze & Excitation fusion (MSEF) module, achieving semantic-aware joint enhancement of illumination and texture. With only 0.87 million parameters, the model significantly outperforms state-of-the-art methods across multiple standard LLIE benchmarks, delivering substantial gains in PSNR and SSIM while maintaining high inference efficiency—thus balancing performance and edge-deployment feasibility.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

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>CWD</bold>) and Multi-Stage Squeeze & Excite Fusion (<bold>MSEF</bold>)—along with the traditional Transformer block, Multi-Headed Self-Attention (<bold>MHSA</bold>). In our method we adopt a dual-path approach, treating chrominance channels <inline-formula><tex-math notation="LaTeX">$U$</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">$V$</tex-math></inline-formula> and luminance channel <inline-formula><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.

Problem

• Enhancing low-light images using lightweight transformer
• Separately processing luminance and chrominance channels
• Outperforming existing methods with lower complexity

Innovation

• Lightweight transformer-based model
• Dual-path YUV channel processing
• Novel Channel-Wise Denoiser blocks