Abstract
The objective of image dehazing is to restore the clear content from a hazy image. However, different parts of the same image pose varying degrees of difficulty for recovery. Existing image dehazing networks treat channel and pixel features equally, making it challenging to handle images with non-uniform haze distribution and weighted channels. To address this limitation, we propose a feature attention module for all-in-one image dehazing. The feature attention module comprises channel attention and pixel attention, offering enhanced flexibility in processing different types of information. Specifically, we perform stitching between adjacent layers in the channel dimension during feature extraction. Subsequently, we apply channel attention and pixel attention on the stitching layer with a large channel dimension. To preserve detailed texture features and minimize information loss from the attention mechanism, we use summation operations between the feature layer obtained after each attention operation and the input layer. Our model prioritizes attention to the dense haze region while maintaining overall brightness. Extensive experiments demonstrate that our method surpasses state-of-the-art dehazing techniques in terms of performance, requiring fewer parameters and FLOPs.
Supported by Liaoning Education Department General Project Foundation (LJKZ0231, LJKZZ20220033); Huaian Natural Science Research Plan Project Foundation (HAB202083).
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Berman, D., Avidan, S.: Non-local image dehazing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1674–1682 (2016)
Cai, B., et al.: Dehazenet: an end-to-end system for single image haze removal. IEEE Trans. Image Process. 25(11), 5187–5198 (2016)
Ren, W., et al.: Gated fusion network for single image dehazing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3253–3261 (2018)
Zhang, H., Patel, V.M.: Densely connected pyramid dehazing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3194–3203 (2018)
Chen, D., et al.: Gated context aggregation network for image dehazing and deraining. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1375–1383. IEEE (2019)
Dong, J., Pan, J.: Physics-based feature dehazing networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 188–204. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58577-8_12
Cui, T., Tian, J., Wang, E., Tang, Y.: Single image dehazing by latent region Segmentation based transmission estimation and weighted L1-norm regularization. IET Image Process 11(2), 145–154 (2016)
Fattal, R.: Single image dehazing. ACM Trans. Graph. 27(3), 1–9 (2008)
Fattal, R.: Dehazing using color-lines. ACM Trans. Graph. 34(1), 1–14 (2014)
Qin, X., et al.: FFA-Net: feature fusion attention network for single image dehazing. Proc. AAAI Conf. Artif. Intelli. 34(7), 11908–11915 (2020)
He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. Mach. Intell. 33(12), 2341–2353 (2010)
Tan, R.T.: Visibility in bad weather from a single image. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2008)
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)
Li, B., et al.: Aod-net: all-in-one dehazing network. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4770–4778 (2017)
Isola, P., Zhu, J.-Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR, pp. 1125–1134 (2017)
Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., Yang, M.-H.: 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). https://doi.org/10.1007/978-3-319-46475-6_10
Li, B., et al.: End-to-end united video dehazing and detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018)
Ren, W., et al.: Gated fusion network for single image dehazing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3253–3261 (2018)
Li, R., et al.: Task-oriented network for image dehazing. IEEE Trans. Image Process. 29, 6523–6534 (2020)
Qu, Y., et al.: Enhanced pix2pix dehazing network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8160–8168 (2019)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Li, B., et al.: RESIDE: A Benchmark for Single Image Dehazing. arXiv e-prints (2017)
Liu, Y., et al.: Learning deep priors for image dehazing. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2492–2500 (2019)
McCartney, E.J.: Optics of the Atmosphere: Scattering by Molecules and Particles. New York (1976)
Narasimhan, S.G., Nayar, S.K.: Vision and the atmosphere. Int. J. Comput. Vision 48(3), 233 (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Dai, Q., Cui, T., Zhang, M., Zhao, X., Hou, B. (2023). All-in-One Image Dehazing Based on Attention Mechanism. In: Yang, H., et al. Intelligent Robotics and Applications. ICIRA 2023. Lecture Notes in Computer Science(), vol 14268. Springer, Singapore. https://doi.org/10.1007/978-981-99-6486-4_5
Download citation
DOI: https://doi.org/10.1007/978-981-99-6486-4_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6485-7
Online ISBN: 978-981-99-6486-4
eBook Packages: Computer ScienceComputer Science (R0)