Curricular contrastive regularization for physics-aware single image dehazing

• Main Authors: ZHENG, Yu, ZHAN, Jiahui, HE, Shengfeng, DU, Yong
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Low-level vision; Computer vision; Codes; Atmospheric modeling; Computational modeling; Scattering; Pattern recognition; Image restoration; Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/8446; https://ink.library.smu.edu.sg/context/sis_research/article/9449/viewcontent/Zheng_Curricular_Contrastive_Regularization_for_Physics_Aware_Single_Image_Dehazing_CVPR_2023_paper.pdf
• Institution: Singapore Management University

Considering the ill-posed nature, contrastive regularization has been developed for single image dehazing, introducing the information from negative images as a lower bound. However, the contrastive samples are non-consensual, as the negatives are usually represented distantly from the clear (i.e.,...