Gated Context Aggregation Network for Image Dehazing and Deraining
arXiv:1811.08747
Abstract
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.
Accepted by WACV 2019, Code released at "https://github.com/cddlyf/GCANet"
References in corpus (10)
- DehazeNet: An End-to-End System for Single Image Haze Removal
- Clearing the Skies: A deep network architecture for single-image rain removal
- Density-aware Single Image De-raining using a Multi-stream Dense Network
- Densely Connected Pyramid Dehazing Network
- StyleBank: An Explicit Representation for Neural Image Style Transfer
- Gated Fusion Network for Single Image Dehazing
- Fast Image Processing with Fully-Convolutional Networks
- Coherent Online Video Style Transfer
- Benchmarking Single Image Dehazing and Beyond
- Deep Exemplar-based Colorization