标题：Gated Context Aggregation Network for Image Dehazing and Deraining
作者：Chen, Dongdong; He, Mingming; Fan, Qingnan; Liao, Jing; Zhang, Liheng; Hou, Dongdong; Yuan, Lu; Hua, Gang
作者机构：[Chen, Dongdong; Hou, Dongdong] Univ Sci & Technol China, Hefei, Anhui, Peoples R China.; [He, Mingming] Hong Kong Univ Sci & Technol, Hong Kong, Pe 更多
会议名称：19th IEEE Winter Conference on Applications of Computer Vision (WACV)
会议日期：JAN 07-11, 2019
来源：2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV)
摘要：Image dehazing aims to recover the uncorrupted content from a hazy image. Instead of leveraging traditional low-level or handcrafted image priors as the restoration constraints, e.g., dark channels and increased contrast, we propose an end-to-end gated context aggregation network to directly restore the final haze-free image. In this network, we adopt the latest smoothed dilation technique to help remove the gridding artifacts caused by the widely-used dilated convolution with negligible extra parameters, and leverage a gated sub-network to fuse the features from different levels. Extensive experiments demonstrate that our method can surpass previous state-of-the-art methods by a large margin both quantitatively and qualitatively. In addition, to demonstrate the generality of the proposed method, we further apply it to the image deraining task, which also achieves the state-of-the-art performance.