Light Attention Lights Your World

Low-light image enhancement remains challenging under spatially non-uniform illumination. Existing unified restoration pipelines often over-enhance bright areas or insufficiently restore severely underexposed regions, while processing highresolution images incurs substantial computational overhead. To address these challenges, we propose $L4$ Net, a **L**ightweight **L**ight-Attention Network for **L**ow-**L**ight Image Enhancement. $L4$ Net performs restoration in the low-resolution feature space using two structurally identical illumination-aware branches that adaptively restore differently illuminated regions. Light-Attention (LA) blocks, the core components of the lightweight $L4$ backbone, integrate global illumination modeling and local feature interactions. A light-guided learning strategy further encourages branch specialization. A super-resolution reconstruction module recovers fine details from compact feature representations. Extensive experiments on multiple low-light benchmarks demonstrate that $L4$ Net achieves state-of-the-art performance with substantially lower computational cost. Deployment on an embedded platform further demonstrates its practicality for resource-constrained low-light vision applications. Code will be released upon publication.