URetinex-Net: Retinex-based Deep Unfolding Network for Low-light Image Enhancement

🤖 Plain-English Summary

Retinex model-based methods have shown to be effective in layer-wise manipulation with well-designed priors for low-light image enhancement. Extensive experiments on real-world low-light images qualitatively and quantitatively demonstrate the effectiveness and superiority of the proposed method over advanced methods.

🔑 Key Findings

• However, the commonly used handcrafted priors and optimization-driven solutions lead to the absence of adaptivity and efficiency.
• To address these issues, in this paper, we propose a Retinex-based deep unfolding network (URetinex-Net), which unfolds an optimization problem into a learnable network to decompose a low-light image into reflectance and illumination layers.
• By formulating the decomposition problem as an implicit priors regularized model, three learning-based modules are carefully designed, responsible for data-dependent initialization, high-efficient unfolding optimization, and user-specified illumination enhancement, respectively.

🔗 Related Resources