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 reconstruction 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.

翻译：非均匀雾气的存在会导致场景模糊、色彩失真、对比度降低等退化现象，从而掩盖纹理细节。现有的均匀去雾方法难以鲁棒地处理雾气的不均匀分布。非均匀去雾的关键挑战在于有效提取非均匀分布特征并以高质量重建雾区细节。本文提出了一种新颖的自 paced 半课程注意力网络（SCANet），用于非均匀图像去雾，该网络专注于增强被雾气遮挡的区域。我们的方法由注意力生成网络和场景重建网络组成。我们利用图像的亮度差异来约束注意力图，并引入自 paced 半课程学习策略以减少训练初期的学习歧义。大量定量和定性实验表明，我们的 SCANet 优于许多现有先进方法。代码已公开于 https://github.com/gy65896/SCANet。