SINET：用于水下图像增强的稀疏驱动可解释神经网络
SINET: Sparsity-driven Interpretable Neural Network for Underwater Image Enhancement
AI总结：
提出基于通道特定卷积稀疏编码模型的可解释网络SINET，通过展开$\ell_1$正则化CSC迭代算法构建SFEB，在水下图像增强中以低3873倍复杂度将PSNR提升1.05 dB。
摘要：
提升水下图像质量对于推进海洋研究与技术至关重要。本工作介绍了一种用于水下图像增强（UIE）任务的稀疏驱动可解释神经网络（SINET）。与纯深度学习方法不同，我们的网络架构基于一种新颖的通道特定卷积稀疏编码（CCSC）模型，确保底层图像增强过程具有良好的可解释性。SINET的关键特征在于它使用三个稀疏特征估计块（SFEB）来估计来自三个颜色通道的显著特征。SFEB的架构通过展开用于求解 $\ell_1$ 正则化卷积稀疏编码（CSC）问题的迭代算法而设计。我们的实验表明，SINET以低3873倍的计算复杂度，将最先进的PSNR值超越了1.05 dB。代码可在以下地址找到：https://github.com/gargi884/SINET-UIE/tree/main。
英文摘要：
Improving the quality of underwater images is essential for advancing marine research and technology. This work introduces a sparsity-driven interpretable neural network (SINET) for the underwater image enhancement (UIE) task. Unlike pure deep learning methods, our network architecture is based on a novel channel-specific convolutional sparse coding (CCSC) model, ensuring good interpretability of the underlying image enhancement process. The key feature of SINET is that it estimates the salient features from the three color channels using three sparse feature estimation blocks (SFEBs). The architecture of SFEB is designed by unrolling an iterative algorithm for solving the $\ell_1$ regularized convolutional sparse coding (CSC) problem. Our experiments show that SINET surpasses state-of-the-art PSNR value by $1.05$ dB with $3873$ times lower computational complexity. Code can be found at: https://github.com/gargi884/SINET-UIE/tree/main.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
