基于多阶段协同处理的水下图像增强

Underwater Image Enhancement Based on Multi-Stage Collaborative Processing

设计了一种多阶段水下图像增强模型,可以同时将空间精细纹理和高级上下文信息两种特征融合。模型由三个阶段组成,前两个阶段采用编码器-解码器结构,第三阶段则采用并行注意子网,所提模型可以同时学习空间细节和上下文信息两种特征,并且引入了监督注意力模块,能够加强特征学习,还设计了一个跨阶段特征融合机制用来巩固前后子网的中间特征。最后将所提模型与其他水下增强模型在同一测试集上运行,从运行结果得出,所提模型处理后的水下图像在主观视觉效果和客观评价质量上均优于大部分对比算法,在Test-1测试集上,峰值信噪比和结构相似度分别达到了26.2962 dB和0.8267。

We propose a multistage underwater image enhancement model that can simultaneously fuse spatial details and contextual information.The model is structured in three stages:the first two stages utilize encoderdecoder configurations,and the third entails a parallel attention subnet.This design enables the model to concurrently learn spatial nuances and contextual data.A supervised attention module is incorporated for enhanced feature learning.Furthermore,a crossstage feature fusion mechanism is designed is used to consolidate the intermediate features from preceding and succeeding subnets.Comparative tests with other underwater enhancement models demonstrate that the proposed model outperforms most extant algorithms in subjective visual quality and objective evaluation metrics.Specifically,on the Test1 dataset,the proposed model realizes a peak signaltonoise ratio of 26.2962 dB and structural similarity index of 0.8267.