Enhanced context encoding for single image raindrop removal  

作　　者：WANG GuoQing YANG Yang XU Xing LI JingJing SHEN HengTao 

机构地区：[1]School of Computer Science and Engineering,University of Electronic Science and Technology of China,Chengdu 610054,China

出　　处：《Science China(Technological Sciences)》2021年第12期2640-2650,共11页中国科学（技术科学英文版）

基　　金：the Joint Funds of the National Natural Science Foundation of China(Grant No.U20B2063);the Sichuan Science and Technology Program(Grant No.2020YFS0057);the Fundamental Research Funds for the Central Universities(Grant No.ZYGX2019Z015)。

摘　　要：Despite the great success achieved by convolutional neural networks in addressing the raindrop removal problem,the still relatively blurry results call for better problem formulations and network architectures.In this paper,we revisited the rainy-to-clean translation networks and identified the issue of imbalanced distribution between raindrops and varied background scenes.None of the existing raindrop removal networks consider this underlying issue,thus resulting in the learned representation biased towards modeling raindrop regions while paying less attention to the important contextual regions.With the aim of learning a more powerful raindrop removal model,we propose learning a soft mask map explicitly for mitigating the imbalanced distribution problem.Specifically,a two stage network is designed with the first stage generating the soft masks,which helps learn a context-enhanced representation in the second stage.To better model the heterogeneously distributed raindrops,a multi-scale dense residual block is designed to construct the hierarchical rainy-to-clean image translation network.Comprehensive experimental results demonstrate the significant superiority of the proposed models over state-of-the-art methods.

关 键 词：raindrop removal imbalance-aware representation learning enhanced context encoding MULTI-SCALE 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]