SINET通过稀疏编码提升水下图像质量，解释性强且计算量极低。
SINET: Sparsity-driven Interpretable Neural Network for Underwater Image Enhancement
- 基于通道特异性稀疏编码设计神经网络，可解释性高
- 相比现有方法提升1.05 dB PSNR，计算量降低3873倍
- 适合需要可解释性与低算力的水下视觉应用
提升水下图像质量对推动海洋研究与技术发展至关重要。本文提出一种稀疏驱动的可解释神经网络（SINET），用于水下图像增强（UIE）任务。不同于纯深度学习方法，SINET的网络架构基于一种新型通道特异性卷积稀疏编码（CCSC）模型，确保了图像增强过程的良好可解释性。SINET的核心特征是利用三个稀疏特征估计块（SFEBs）从三色通道中估计显著特征。SFEB的结构通过展开求解ℓ₁正则化卷积稀疏编码（CSC）问题的迭代算法设计而成。实验表明，SINET在峰值信噪比（PSNR）上超越当前最优水平1.05 dB，同时计算复杂度降低3873倍。代码地址：https://github.com/gargi884/SINET-UIE/tree/main。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。