Mask-shadownet: Toward shadow removal via masked adaptive instance normalization

• Main Authors: HE, Shengfeng, PENG, Bing, DONG, Junyu, DU, Yong
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Lighting; Feature extraction; Training; Neural networks; task analysis; Predictive models; Adaptation models; Deep neural network; shadow removal; masked adaptive instance normalization; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/7874
• Institution: Singapore Management University

Shadow removal is an important yet challenging task in image processing and computer vision. Existing methods are limited in extracting good global features due to the interference of shadow. And also, most of them ignore a fact that features inside and outside the shaded area should be treated disp...