Two-Stage Image Dehazing with Depth Information and Cross-Scale Non-Local Attention
Cheng Youn Lu, Li Zhao · 2021 IEEE International Conference on Big Data (Big Data) · 2021
Image dehazing using learning-based methods has achieved state-of-the-art performance in recent years. However, most of previous models for low-level vision tasks are always based on single-stage design. There is an issue with majority image dehazing approaches: a complex balance problem between spatial details and high-level contextualized information while recovering images. To address this issue, we propose a two-stage network, which consists of encoder-decoder subnetwork and original-resolution one. Specifically, the encoder-decoder subnetwork first learns the contextualized features, and then the features are combined with the original-resolution subnet that maintains enriched high-resolution features. For information exchange between two stages, we introduce a Cross-Scale Non-Local (CS-NL) attention module that can search more high-frequency details from low-resolution images in encoder-decoder stage and transfer directly them to the next stage. Moreover we embed the spatial feature transform (SFT) module into original-resolution subnet, which is incorporated with depth information to better achieve the purpose of image dehazing. The two-stage network, named as TSDCN-Net, which demonstrates its effectiveness according extensive experiments. The TSDCN-Net surpasses previous state-of-the-art single image dehazing methods by a large margin both quantitatively and qualitatively.