Lighting dark images with linear attention and decoupled network

• Published in: Pattern recognition Vol. 170; p. 111930
• Main Authors: Zheng, Jiazhang, Liao, Qiuping, Li, Lei, Li, Cheng, Liu, Yangxing
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.02.2026
• Subjects: Attention mechanism; Lightweight network; Low-light raw image enhancement; Attention mechanism; Lightweight network; Low-light raw image enhancement
• ISSN: 0031-3203
• DOI: 10.1016/j.patcog.2025.111930

Nighttime photography encounters escalating challenges in extremely low-light conditions, primarily attributable to the ultra-low signal-to-noise ratio. For real-world deployment, a practical solution must not only produce visually appealing results but also require minimal computation. However, most existing methods are either focused on improving restoration performance or employ lightweight models at the cost of quality. This paper proposes a lightweight network that outperforms existing state-of-the-art (SOTA) methods in low-light enhancement tasks while minimizing computation. The proposed network incorporates Siamese Self-Attention Block (SSAB) and Skip-Channel Attention (SCA) modules, which enhance the model’s capacity to aggregate global information and are well-suited for high-resolution images. Additionally, based on our analysis of the low-light image restoration process, we propose a Two-Stage Framework that achieves superior results. Our model can restore a UHD 4K resolution image with minimal computation while keeping SOTA restoration quality. •Lightweight network restores 4K ultra-dark images with SOTA quality and efficiency.•SSAB aggregates compact global context with linear scaling to image size.•SCA fuses encoder-decoder cues to resolve cross-layer ambiguity and enhance quality.•Two-stage RAW-sRGB pipeline decouples noise and brightness for superior results.