SDRNet: An end-to-end shadow detection and removal network
作者：
Highlights：
• SDRNet can complete the shadow detection and removal tasks in a unified network.
• SDRNet highly shares features and have no additional computational complexity.
• A multi-scale global feature module is used to solve shadow area problems.
• Shadow segmentation accuracy can be improved by using the image direction feature.
• Superior performance can be achieved in both shadow detection and removal tasks.
摘要
•SDRNet can complete the shadow detection and removal tasks in a unified network.•SDRNet highly shares features and have no additional computational complexity.•A multi-scale global feature module is used to solve shadow area problems.•Shadow segmentation accuracy can be improved by using the image direction feature.•Superior performance can be achieved in both shadow detection and removal tasks.
论文关键词：Shadow detection,Shadow removal,Multi-scale,Direction features,SDRNet network
论文评审过程：Received 8 August 2019, Revised 10 March 2020, Accepted 10 March 2020, Available online 12 March 2020, Version of Record 13 March 2020.
论文官网地址：https://doi.org/10.1016/j.image.2020.115832
