🤖 AI Summary
To address the demand for lightweight low-light image enhancement on resource-constrained edge devices, this paper proposes CPGA-Net+, an efficient network integrating atmospheric scattering–driven attention with channel-wise and gamma-correction priors. Methodologically, it introduces a novel plug-in attention mechanism guided by the atmospheric scattering model; theoretically establishes that enhancement can be decoupled into physical scene restoration and brightness boosting; and adopts model reparameterization and module simplification to reduce computational cost by over 67%. Trained via a hybrid supervised–unsupervised strategy, CPGA-Net+ consistently outperforms state-of-the-art lightweight methods across multiple benchmarks, achieving superior trade-offs among PSNR, SSIM, and perceptual quality. The design ensures both high fidelity and ultra-low latency, making it particularly suitable for edge deployment.
📝 Abstract
Enhancing low-light images remains a critical challenge in computer vision, as does designing lightweight models for edge devices that can handle the computational demands of deep learning. In this article, we introduce an extended version of the Channel-Prior and Gamma-Estimation Network (CPGA-Net), termed CPGA-Net+, which incorporates an attention mechanism driven by a reformulated Atmospheric Scattering Model and effectively addresses both global and local image processing through Plug-in Attention with gamma correction. These innovations enable CPGA-Net+ to achieve superior performance on image enhancement tasks for supervised and unsupervised learning, surpassing lightweight state-of-the-art methods with high efficiency. Furthermore, we provide a theoretical analysis showing that our approach inherently decomposes the enhancement process into restoration and lightening stages, aligning with the fundamental image degradation model. To further optimize efficiency, we introduce a block simplification technique that reduces computational costs by more than two-thirds. Experimental results validate the effectiveness of CPGA-Net+ and highlight its potential for applications in resource-constrained environments.