Abstract
Many light field image super-resolution networks are proposed to directly aggregate the features of different low-resolution sub-aperture images (SAIs) to reconstruct high-resolution sub-aperture images. However, most of them ignore aligning different SAI’s features before aggregation, which will generate sub-optimal light field image super-resolution results. To handle this limitation, we design a mutual attention mechanism to align the SAI’s features and propose a Light Field Mutual Attention Guidance Network (LF-MAGNet) constructed by multiple Mutual Attention Guidance blocks (MAGs) in a cascade manner. MAG achieves the mutual attention mechanism between center SAI and any surrounding SAI with two modules: the center attention guidance module (CAG) and the surrounding attention guidance module (SAG). Specifically, CAG first aligns the center-SAI features and any surrounding SAI features with the attention mechanism and then guides the surrounding SAI feature to learn from the center-SAI features, generating refined-surrounding SAI features. SAG aligns the refined-surrounding SAI feature and the original surrounding SAI feature and guides the refined surrounding SAI feature to learn from the original surrounding SAI features, generating the final outputs of MAG. With the help of MAG, LF-MAGNet can efficiently utilize different SAI features and generate high-quality light field image super-resolution results. Experiments are performed on commonly-used light field image super-resolution benchmarks. Qualitative and quantitative results prove the effectiveness of our LF-MAGNet.
This is a student paper.
This work is supported by the National Natural Science Foundation of China (No. 61273273), by the National Key Research and Development Plan (No. 2017YFC0112001), and by China Central Television (JG2018-0247).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alain, M., Smolic, A.: Light field super-resolution via lfbm5d sparse coding. In: ICIP, pp. 2501–2505 (2018)
Dai, T., Cai, J., Zhang, Y., Xia, S.T., Zhang, L.: Second-order attention network for single image super-resolution. In: CVPR, pp. 11065–11074 (2019)
Honauer, K., Johannsen, O., Kondermann, D., Goldluecke, B.: A dataset and evaluation methodology for depth estimation on 4D light fields. In: ACCV, pp. 19–34 (2016)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132–7141 (2018)
Huang, F.C., et al.: The light field stereoscope-immersive computer graphics via factored near-eye field displays with focus cues. SIGGRAPH (2015)
Jin, J., Hou, J., Chen, J., Kwong, S.: Light field spatial super-resolution via deep combinatorial geometry embedding and structural consistency regularization. In: CVPR, pp. 2260–2269 (2020)
Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. In: CVPR, pp. 1646–1654 (2016)
Le Pendu, M., Jiang, X., Guillemot, C.: Light field inpainting propagation via low rank matrix completion. IEEE TIP 27(4), 1981–1993 (2018)
Lim, B., Son, S., Kim, H., Nah, S., Mu Lee, K.: Enhanced deep residual networks for single image super-resolution. In: CVPRW, pp. 136–144 (2017)
Liu, J., Tang, J., Wu, G.: Residual feature distillation network for lightweight image super-resolution. arXiv preprint arXiv:2009.11551 (2020)
Lu, X., Wang, W., Danelljan, M., Zhou, T., Shen, J., Van Gool, L.: Video object segmentation with episodic graph memory networks. In: ECCV, pp. 661–679 (2020)
Park, J., Woo, S., Lee, J.Y., Kweon, I.S.: Bam: Bottleneck attention module. arXiv preprint arXiv:1807.06514 (2018)
Rerabek, M., Ebrahimi, T.: New light field image dataset. In: 8th International Conference on Quality of Multimedia Experience. No. CONF (2016)
Rossi, M., Frossard, P.: Geometry-consistent light field super-resolution via graph-based regularization. IEEE TIP 27(9), 4207–4218 (2018)
Sheng, H., Zhang, S., Cao, X., Fang, Y., Xiong, Z.: Geometric occlusion analysis in depth estimation using integral guided filter for light-field image. IEEE TIP 26(12), 5758–5771 (2017)
Shi, J., Jiang, X., Guillemot, C.: A framework for learning depth from a flexible subset of dense and sparse light field views. IEEE TIP 28(12), 5867–5880 (2019)
Vaish, V., Adams, A.: The (new) stanford light field archive. Computer Graphics Laboratory, Stanford University 6(7) (2008)
Wang, B., Yang, L., Zhao, Y.: POLO: learning explicit cross-modality fusion for temporal action localization. IEEE Signal Process. Lett. 28, 503–507 (2021)
Wang, W., Zhou, T., Qi, S., Shen, J., Zhu, S.C.: Hierarchical human semantic parsing with comprehensive part-relation modeling. IEEE TPAMI (2021)
Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR, pp. 7794–7803 (2018)
Wang, Y., Wang, L., Yang, J., An, W., Yu, J., Guo, Y.: Spatial-angular interaction for light field image super-resolution. In: ECCV, pp. 290–308 (2020)
Wang, Y., Yang, J., Wang, L., Ying, X., Wu, T., An, W., Guo, Y.: Light field image super-resolution using deformable convolution. IEEE TIP 30, 1057–1071 (2020)
Wang, Y., Liu, F., Zhang, K., Hou, G., Sun, Z., Tan, T.: LFNet: a novel bidirectional recurrent convolutional neural network for light-field image super-resolution. IEEE TIP 27(9), 4274–4286 (2018)
Wanner, S., Meister, S., Goldluecke, B.: Datasets and benchmarks for densely sampled 4D light fields. Vis. Modell. Visual. 13, 225–226 (2013)
Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: ECCV, pp. 3–19 (2018)
Yang, L., Peng, H., Zhang, D., Fu, J., Han, J.: Revisiting anchor mechanisms for temporal action localization. IEEE TIP 29, 8535–8548 (2020)
Yeung, H.W.F., Hou, J., Chen, X., Chen, J., Chen, Z., Chung, Y.Y.: Light field spatial super-resolution using deep efficient spatial-angular separable convolution. IEEE TIP 28(5), 2319–2330 (2018)
Yoon, Y., Jeon, H.G., Yoo, D., Lee, J.Y., Kweon, I.S.: Light-field image super-resolution using convolutional neural network. IEEE Signal Process. Lett. 24(6), 848–852 (2017)
Yu, J.: A light-field journey to virtual reality. IEEE Multimedia 24(2), 104–112 (2017)
Yuan, Y., Cao, Z., Su, L.: Light-field image superresolution using a combined deep CNN based on EPI. IEEE Signal Process. Lett. 25(9), 1359–1363 (2018)
Zhang, S., Lin, Y., Sheng, H.: Residual networks for light field image super-resolution. In: CVPR, pp. 11046–11055 (2019)
Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y.: Image super-resolution using very deep residual channel attention networks. In: ECCV, pp. 286–301 (2018)
Zhou, T., Li, J., Wang, S., Tao, R., Shen, J.: MATNet: motion-attentive transition network for zero-shot video object segmentation. IEEE TIP 29, 8326–8338 (2020)
Zhou, T., Qi, S., Wang, W., Shen, J., Zhu, S.C.: Cascaded parsing of human-object interaction recognition. IEEE TPAMI (2021)
Zhou, T., Wang, S., Zhou, Y., Yao, Y., Li, J., Shao, L.: Motion-attentive transition for zero-shot video object segmentation. In: AAAI, pp. 13066–13073 (2020)
Zhou, T., Wang, W., Liu, S., Yang, Y., Van Gool, L.: Differentiable multi-granularity human representation learning for instance-aware human semantic parsing. In: CVPR, pp. 1622–1631 (2021)
Zhu, H., Wang, Q., Yu, J.: Occlusion-model guided antiocclusion depth estimation in light field. IEEE J. Selected Top. Signal Process. 11(7), 965–978 (2017)
Zhu, H., Zhang, Q., Wang, Q.: 4D light field superpixel and segmentation. In: CVPR, pp. 6384–6392 (2017)
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
Wang, Z., Lu, Y., Zhang, Y., Lu, H., Wang, S., Wang, B. (2021). LF-MAGNet: Learning Mutual Attention Guidance of Sub-Aperture Images for Light Field Image Super-Resolution. In: Ma, H., et al. Pattern Recognition and Computer Vision. PRCV 2021. Lecture Notes in Computer Science(), vol 13021. Springer, Cham. https://doi.org/10.1007/978-3-030-88010-1_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-88010-1_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88009-5
Online ISBN: 978-3-030-88010-1
eBook Packages: Computer ScienceComputer Science (R0)