The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing
Preprint
Abstract
We propose a novel deep neural network architecture for the challenging problem of single image dehazing, which aims to recover the clear image from a degraded hazy image. Instead of relying on hand-crafted image priors or explicitly estimating the components of the widely used atmospheric scattering model, our end-to-end system directly generates the clear image from an input hazy image. The proposed network has an encoder-decoder architecture with skip connections and instance normalization. We adopt the convolutional layers of the pre-trained VGG network as encoder to exploit the representation power of deep features, and demonstrate the effectiveness of instance normalization for image dehazing. Our simple yet effective network outperforms the state-of-the-art methods by a large margin on the benchmark datasets.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Semantic Foggy Scene Understanding with Synthetic DataInternational Journal of Computer Vision, 2018
- A Cascaded Convolutional Neural Network for Single Image DehazingIEEE Access, 2018
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Image Style Transfer Using Convolutional Neural Networks2016
- Robust Image and Video Dehazing with Visual Artifact Suppression via Gradient Residual Minimization2016
- Deep Residual Learning for Image Recognition2016
- Non-local Image Dehazing2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Investigating Haze-Relevant Features in a Learning Framework for Image Dehazing2014
- Visibility in bad weather from a single image2008