Abstract
The goal of the stereoscopic image super-resolution (SR) is to reconstruct a pair of high-resolution (HR) images from corresponding low-resolution (LR) images. The existing stereo SR methods based on convolutional neural network (CNN) benefit from additional information from a different viewpoint to some extent. However, they cannot make good use of the complementary information from the different viewpoint, resulting in a lack of textures and details. The unevenly distributed features from left and right images were treated equally. To overcome the above difficulties, we put forward a stereo attention graph neural network (SA-GNN), which can extract reliable priors non-locally and fuse consistent contents adaptively cross different viewpoints. SA-GNN contains a series of stereo graph neural networks (SGNN), which alternate iteratively between in-view graph and cross-view graph under the aggregation and update mechanism of graph neural networks (GNN) to enhance SR performance. The comparison experiment results on four public datasets demonstrate that our SA-GNN outperforms the state-of-the-art methods.
This work was supported in part by the National Natural Science Foundation of China under Grant 91848107, and in part by the National Key Research and Development Program of China under Grant 2020YFB2103501.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 184–199. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10593-2_13
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354–3361. IEEE (2012)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/1512.03385 (2015). http://arxiv.org/abs/1512.03385
He, X., Liu, Q., Yang, Y.: MV-GNN: multi-view graph neural network for compression artifacts reduction. IEEE Trans. Image Process. 29, 6829–6840 (2020)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Jeon, D.S., Baek, S.H., Choi, I., Kim, M.H.: Enhancing the spatial resolution of stereo images using a parallax prior. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1721–1730 (2018)
Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694–711. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_43
Keys, R.: Cubic convolution interpolation for digital image processing. IEEE Trans. Acoust. Speech Signal Process. 29(6), 1153–1160 (1981)
Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 136–144 (2017)
Mei, Y., Fan, Y., Zhou, Y., Huang, L., Huang, T.S., Shi, H.: Image super-resolution with cross-scale non-local attention and exhaustive self-exemplars mining. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5690–5699 (2020)
Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3061–3070 (2015)
Plötz, T., Roth, S.: Neural nearest neighbors networks. Adv. Neural. Inf. Process. Syst. 31, 1087–1098 (2018)
Qi, X., Liao, R., Jia, J., Fidler, S., Urtasun, R.: 3D graph neural networks for RGBD semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5199–5208 (2017)
Scharstein, D., et al.: High-resolution stereo datasets with subpixel-accurate ground truth. In: Jiang, X., Hornegger, J., Koch, R. (eds.) GCPR 2014. LNCS, vol. 8753, pp. 31–42. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-11752-2_3
Simonovsky, M., Komodakis, N.: Dynamic edge-conditioned filters in convolutional neural networks on graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3693–3702 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Song, W., Choi, S., Jeong, S., Sohn, K.: Stereoscopic image super-resolution with stereo consistent feature. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12031–12038 (2020)
Wang, L., et al.: Learning parallax attention for stereo image super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12250–12259 (2019)
Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794–7803 (2018)
Wang, Y., Wang, L., Yang, J., An, W., Guo, Y.: Flickr1024: a large-scale dataset for stereo image super-resolution. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (2019)
Wang, Y., Ying, X., Wang, L., Yang, J., An, W., Guo, Y.: Symmetric parallax attention for stereo image super-resolution. arXiv preprint arXiv:2011.03802 (2020)
Ying, X., Wang, Y., Wang, L., Sheng, W., An, W., Guo, Y.: A stereo attention module for stereo image super-resolution. IEEE Signal Process. Lett. 27, 496–500 (2020)
Zeiler, M.D., Taylor, G.W., Fergus, R.: Adaptive deconvolutional networks for mid and high level feature learning. In: 2011 International Conference on Computer Vision, pp. 2018–2025. IEEE (2011)
Zhang, Y., Li, K., Li, K., Zhong, B., Fu, Y.: Residual non-local attention networks for image restoration. arXiv preprint arXiv:1903.10082 (2019)
Zhang, Y., Tian, Y., Kong, Y., Zhong, B., Fu, Y.: Residual dense network for image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2472–2481 (2018)
Zhou, S., Zhang, J., Zuo, W., Loy, C.C.: Cross-scale internal graph neural network for image super-resolution. arXiv preprint arXiv:2006.16673 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, H., Liu, Q., Yang, Y. (2021). SA-GNN: Stereo Attention and Graph Neural Network for Stereo Image Super-Resolution. In: Peng, Y., Hu, SM., Gabbouj, M., Zhou, K., Elad, M., Xu, K. (eds) Image and Graphics. ICIG 2021. Lecture Notes in Computer Science(), vol 12890. Springer, Cham. https://doi.org/10.1007/978-3-030-87361-5_33
Download citation
DOI: https://doi.org/10.1007/978-3-030-87361-5_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87360-8
Online ISBN: 978-3-030-87361-5
eBook Packages: Computer ScienceComputer Science (R0)