Conventional CNNs-based dehazing models suffer from two essential issues: the dehazing framework (limited in interpretability) and the convolution layers (content-independent and ineffective to learn long-range dependency information). In this paper, firstly, we propose a new complementary feature enhanced framework, in which the complementary features are learned by several complementary subtasks and then together serve to boost the performance of the primary task. One of the prominent advantages of the new framework is that the purposively chosen complementary tasks can focus on learning weakly dependent complementary features, avoiding repetitive and ineffective learning of the networks. We design a new dehazing network based on such a framework. Specifically, we select the intrinsic image decomposition as the complementary tasks, where the reflectance and shading prediction subtasks are used to extract the color-wise and texture-wise complementary features. To effectively aggregate these complementary features, we propose a complementary features selection module (CFSM) to select the more useful features for image dehazing. Furthermore, we introduce a new version of vision transformer block, named Hybrid Local-Global Vision Transformer (HyLoG-ViT), and incorporate it within our dehazing networks. The HyLoG-ViT block consists of the local and the global vision transformer paths used to capture local and global dependencies. As a result, the HyLoG-ViT introduces locality in the networks and captures the global and long-range dependencies. Extensive experiments on homogeneous, non-homogeneous, and nighttime dehazing tasks reveal that the proposed dehazing network can achieve comparable or even better performance than CNNs-based dehazing models.
翻译:以CNN为基础的常规脱色模型有两个基本问题:脱色框架(解释能力有限)和变异层(在学习远距离依赖性信息方面是独立和无效的 ) 。 在本文件中,首先,我们提出一个新的互补特征强化框架,通过几个互补的子任务学习互补特征,然后一起促进主要任务的绩效。新框架的一个突出优势是,有目的地选择的互补任务可以侧重于学习依赖性薄弱的互补特征,避免网络的重复和无效学习。我们根据这样一个框架设计一个新的脱色网络。具体地说,我们选择内在图像脱色作为互补任务,在其中,用反光和阴影的预测子任务来提取颜色化和文字化的互补特征,然后一起促进这些互补特征的有效整合。我们提出一个互补特征选择模块(CFSMSM),以选择更有用的图像淡化功能。此外,我们引入了新版本的视野变异模型,即地方-全球混合视野变异性网络(HYLO-G-T),以及全球变异性网络(HY-G-LE-LV-LA-LA-LA-LV-LA-LA-LA-LA-LA-LA-LV-LV-LV-I-LV-LV-LV-LS-L-L-LV-L-L-LV-LV-LV-S-S-LV-LV-LV-S-S-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-L-