Rethinking Theoretical Illumination for Efficient Low-Light Image Enhancement
This work addresses the problem of computational efficiency in low-light image enhancement for edge devices, presenting an incremental improvement over existing methods.
The paper tackles efficient low-light image enhancement for edge devices by introducing CPGA-Net+, which includes theoretical attention mechanisms for local and global processing, resulting in a lightweight version that reduces computational costs by over two-thirds and a stronger version that balances processing capabilities.
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. This article introduces an extended version of the Channel-Prior and Gamma-Estimation Network (CPGA-Net), termed CPGA-Net+, incorporating the theoretically-based Attentions for illumination in local and global processing. Additionally, we assess our approach through a theoretical analysis of the block design by introducing both an ultra-lightweight and a stronger version, following the same design principles. The lightweight version significantly reduces computational costs by over two-thirds by utilizing the local branch as an auxiliary component. Meanwhile, the stronger version achieves an impressive balance by maximizing local and global processing capabilities. Our proposed methods have been validated as effective compared to recent lightweight approaches, offering superior performance and scalable solutions with limited computational resources.