Multi-feature Fusion Network for Single Image Dehazing
Authors: 
Jie Luo, Tong Chang, Qirong BoAuthors Info & Claims
Pages 127 - 136
Abstract
Existing image dehazing methods consider the learning-based methods as the mainstream. Most of them are trained on synthetic dataset, and may not be able to efficiently transfer to real outdoor scenes. In order to further improve the dehazing effect of the model in real outdoor scenes, this paper proposes an end-to-end Multi-Feature Fusion Network for Single Image Dehazing (MFFN). The proposed network combines the prior-based methods and learning-based methods. This paper first uses the method of supporting backpropagation in order to directly extract the dark channel prior and color attenuation prior features. It then designs a Multi-Feature Adaptive Fusion Module (MFAFM) which can adaptively fuse and enhance the two prior features. Finally, the prior features are added to the decoding stage of the backbone network in a multi-scale manner. The experimental results on the synthetic dataset and real-world dataset demonstrate that the proposed model performs favorably against the state-of-the-art dehazing algorithms.
References
[1]
Narasimhan SG and Nayar SK Vision and the atmosphere Int. J. Comput. Vis. 2002 48 3 233-254
[2]
Cantor, A.: Optics of the atmosphere–scattering by molecules and particles. IEEE J. Quantum Electron., 698–699 (1978)
[3]
He K, Sun J, and Tang X Single image haze removal using dark channel prior IEEE Trans. Pattern Anal. Mach. Intell. 2011 33 12 2341-2353
[4]
Liu, Q., Gao, X., He, L., Lu, W.: Single image dehazing with depth aware non-local total variation regularization. IEEE Trans. Image Process, 27, 5178–5191 (2018)
[5]
Fattal, R.: Dehazing using color-lines. ACM Trans. Graph. 34(1), Article no. 13 (2014)
[6]
Meng, G., Wang, Y., Duan, J., Xiang, S., Pan, C.: Efficient image dehazing with boundary constraint and contextual regularization. In: Proceeding IEEE International Conference Computer Vision, pp. 617–624 (2013)
[7]
Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., Yang, MH.: Single image dehazing via multi-scale convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 154–169. Springer, Cham (2016).
[8]
Zhang, H., Patel, V.M.: Densely connected pyramid dehazing network. In: Proceeding IEEE Conference Computer Vision Pattern Recognition, pp. 3194–3203 (2018)
[9]
Ren, W. et al.: Gated fusion network for single image dehazing. In: Proceeding IEEE/CVF Conference Computer Vision Pattern Recognition, pp. 3253–3261 (2018)
[10]
Li, B., Peng, X., Wang, Z., Xu, J., Feng D.: AOD-Net: all-in-one dehazing network. In: Proceeding IEEE International Conference Computer Vision, pp. 4780–4788 (2017)
[11]
Qu, Y., Chen, Y., Huang, J., Xie, Y.: Enhanced Pix2pix dehazing network. In: Proceeding IEEE/CVF Conference Computer Vision Pattern Recognition, pp. 8152–8160 (2019)
[12]
Liu, X., Ma, Y., Shi, Z., Chen, J.: GridDehazeNet: attention-based multi-scale network for image dehazing. In: Proceeding IEEE International Conference Computer Vision, pp. 7313–7322 (2019)
[13]
Qin, X., Wang, Z., Bai, Y., Xie, X., Jia, H.: FFA-Net: feature fusion attention network for single image dehazing. In: Proceeding AAAI Conference Artificial Intelligence, pp. 11908–11915 (2020)
[14]
Luo, J., Bu, Q., Zhang, L., Feng, J.: Global feature fusion attention network for single image dehazing. In: IEEE International Conference on Multimedia & Expo Workshops, pp. 1–6 (2021)
[15]
Zhu, Q., Mai, J., Shao, L.: A fast single image haze removal algorithm using color attenuation prior. IEEE Trans. Image Process. 24(11), 3522–3533 (2015)
[16]
Li B et al. Benchmarking single-image dehazing and beyond IEEE Trans. Image Process. 2019 28 1 492-505
[17]
Dong, H., Pan, J., Xiang, L., Hu, Z., Zhang, X.: Multi-scale boosted dehazing network with dense feature fusion. In: Proceeding IEEE/CVF Conference Computer Vision Pattern Recognition (2020)
[18]
Ancuti, C.O., Ancuti, C., De Vleeschouwer, C., Timofte, R.: O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images. In: Proceeding Conference Computer Vision Pattern Recognition Workshops, pp. 88–97 (2018)
[19]
Ancuti, C.O., Ancuti, C., Timofte, R.: NH-HAZE: an image dehazing benchmark with non-homogeneous hazy and haze-free images. In: Proceeding IEEE/CVF Conference Computer Vision Pattern Recognition (2020)
[20]
Ancuti, C.O., Ancuti, C., Vasluianu, F.-A., Timofte, R.: Ntire 2020 challenge on nonhomogeneous dehazing. In: Proceeding Conference Computer Vision Pattern Recognition Workshops (2020)
[21]
Chen, D., et al.: Gated context aggregation network for image dehazing and deraining. In: IEEE Winter Conference on Applications of Computer Vision, pp. 1375–1383 (2019)
[22]
Yi, Q., Li, J., Fang, F., Jiang, A., Zhang, G.: Efficient and accurate multi-scale topological network for single image dehazing. IEEE Trans. Multimedia (2021)
[23]
Li, L., Dong, Y., Ren, W., Pan, J., Gao, C., Sang, N.: Semi-supervised image dehazing. IEEE Trans. Image Process. 29, 2766–2779 (2019)
[24]
Shao, Y., Li, L., Ren, W., Gao, C., Sang, N.: Domain adaptation for image dehazing. In: Proceeding IEEE/CVF Conference Computer Vision Pattern Recognition, pp. 2805–2814 (2020)
[25]
He, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., Li, M.: Bag of tricks for image classification with convolutional neural networks. In: Proceeding IEEE/CVF Conference Computer Vision Pattern Recognition, pp. 558–567 (2019)
Index Terms
- Multi-feature Fusion Network for Single Image Dehazing
Index terms have been assigned to the content through auto-classification.
Recommendations
Multi-scale recurrent attention gated fusion network for single image dehazing
Highlights- We present the Multi-scale Recurrent Attention Gated Fusion Network (MRAGFN) as an end-to-end solution for tackling the image dehazing task.
- We develop the Global Feature Extraction Module (GFEM), which utilizes dilated convolutions of ...
AbstractThe purpose of single image dehazing is to eliminate the bad influence of haze on images, so as to maintain more scene information of images. In recent years, the convolutional neural networks (CNN) have made significant contributions to single ...
A multi-scale fusion scheme based on haze-relevant features for single image dehazing
Highlights- We propose a multi-scale pyramid fusion scheme for single image dehazing.
- We ...
AbstractOutdoor images are often degraded by aerosols suspending in atmosphere in bad weather conditions like haze. To cope with this phenomenon, researchers have proposed many approaches and single image based techniques draw attention ...
Bilateral filter-oriented multi-scale CNN fusion model for single image dehazing
This paper proposes a bilateral filter-oriented multi-scale CNN fusion model for single image dehazing. A multi-scale CNN model with low frequency and high frequency dehazing sub-network is designed. First, the haze image is decomposed by bilateral ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Oct 2022
751 pages
ISBN:978-3-031-18915-9
DOI:10.1007/978-3-031-18916-6
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 14 October 2022
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 20 Nov 2024
Other Metrics
Citations
View Options
View options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in