Gated Context Aggregation Network for Image Dehazing and Deraining
By Dongdong Chen, Mingming He, Qingnan Fan, Jing Liao, Liheng Zhang, Dongdong Hou, Lu Yuan, Gang Hua. IEEE Workshop/Winter Conference on Applications of Computer Vision, 2018
756 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition, Media Technology
View Paper: https://www.semanticscholar.org/paper/04ad242b95b2d3127680e790b82030ba9b9d2cce
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Ming-Hsuan Yang
- Luc Van Gool
- Dacheng Tao
- Lei Zhang
- Chen Change Loy
- Peyman Milanfar
- Jin-shan Pan
- Radu Timofte
In Media Technology
- Ming-Hsuan Yang
- Jin-shan Pan
- Peyman Milanfar
- Zhengzhong Tu
- Zhe Hu
- Radu Timofte
- Hossein Talebi
- Feng Yang
Citations in the corpus
- Omni-Kernel Network for Image Restoration (2024, background): “In recent years, convolutional neural networks (CNNs) have achieved superior performance over traditional algorithms on image restoration tasks by learning generalizable priors from collected large-scale datasets (Chen et al. 2019).”
- Vision Transformers for Single Image Dehazing (2022, methodology): “And current methods [13], [14], [15], [16], [17], [18], [19], [20], [21] prefer to predict the latent haze-free image or the residuals of the haze-free image versus the hazy image since it tends to achieve better perfor-”
- MAXIM: Multi-Axis MLP for Image Processing (2022, background): “Visual comparisons for image dehazing on SOTS indoor testset [45] among GCANet [13], GridDehaze [54], DuRN [55], MSBDN [22], FFA-Net [72], and our MAXIM-2S.”
- Multi-Scale Boosted Dehazing Network With Dense Feature Fusion (2020, background): “(e2) GFN [14] (f2) GCANet [2] (g2) DuRN [11] (h2) Ours Figure C.”