通信学报2024，Vol.45Issue(5)：178-190,13.DOI:10.11959/j.issn.1000-436x.2024099
特征分离和非阴影信息引导的阴影去除网络
Feature separation and non-shadow information-guided shadow removal network
摘要
Abstract
To tackle the performance bottlenecks and color deviation issues stemming from current shadow removal methods,a feature separation and non-shadow information guided shadow removal network(FSNIG-ShadowNet)was constructed.In the separation and reconstruction stage,the shadow image was separated into direct light and ambient light using self-reconstruction supervision,with decoupling of lighting types and reflectance.Subsequently,a decoder was employed to re-couple the separated features to yield shadow-free images.In the refinement stage,the network fo-cused on the adjacent regions of shadow and non-shadow,incorporating a local region adaptive normalization module to transfer the color priors of local non-shadow region to shadow regions for mitigating color deviation between the two re-gions.Experimental results demonstrate that the proposed FSNIG-ShadowNet achieves competitive results compared to other state-of-the-art methods.关键词
阴影去除/特征分离/自重建/颜色先验Key words
shadow removal/feature separation/self-reconstruction/color prior分类
信息技术与安全科学引用本文复制引用
黄颖,房少杰,程彬,姜茂,钱鹰..特征分离和非阴影信息引导的阴影去除网络[J].通信学报,2024,45(5):178-190,13.基金项目
国家自然科学基金重点项目(No.62331008) The National Natural Science Foundation Key Project of China (No.62331008) （No.62331008）
