SCANet: Self-paced semi-curricular attention network for non-homogeneous image dehazing

• Main Authors: GUO, Yu, GAO, Yuan, LIU, Ryan Wen, LU, Yuxu, QU, Jingxiang, HE, Shengfeng, REN Wenqi
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Environmental Sciences; Graphics and Human Computer Interfaces; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/8095; https://ink.library.smu.edu.sg/context/sis_research/article/9098/viewcontent/Guo_SCANet_Self_Paced_Semi_Curricular_Attention_Network_for_Non_Homogeneous_Image_Dehazing_CVPRW_2023_paper.pdf
• Institution: Singapore Management University

The presence of non-homogeneous haze can cause scene blurring, color distortion, low contrast, and other degradations that obscure texture details. Existing homogeneous dehazing methods struggle to handle the non-uniform distribution of haze in a robust manner. The crucial challenge of non-homogeneous dehazing is to effectively extract the non-uniform distribution features and reconstruct the details of hazy areas with high quality. In this paper, we propose a novel self-paced semi-curricular attention network, called SCANet, for non-homogeneous image dehazing that focuses on enhancing haze-occluded regions. Our approach consists of an attention generator network and a scene re-construction network. We use the luminance differences of images to restrict the attention map and introduce a self-paced semi-curricular learning strategy to reduce learning ambiguity in the early stages of training. Extensive quantitative and qualitative experiments demonstrate that our SCANet outperforms many state-of-the-art methods. The code is publicly available at https://github.com/ gy65896/SCANet.