Gated Context Aggregation Network for Image Dehazing and Deraining
This addresses the problem of recovering clear images from hazy or rainy conditions for computer vision applications, representing an incremental improvement with a novel network design.
The paper tackles image dehazing by proposing an end-to-end gated context aggregation network that directly restores haze-free images, surpassing previous state-of-the-art methods by a large margin both quantitatively and qualitatively, and also achieves state-of-the-art performance on image deraining.
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. Code has been made available at https://github.com/cddlyf/GCANet.