Abstract
Light field (LF) camera sensors often face a trade-off between angular resolution and spatial resolution when shooting. High spatial resolution image arrays often result in lower angular resolution, and vice versa. In order to obtain high spatial resolution and at the same time have high angular resolution. In this paper, we propose an improved 4D convolutional neural network (CNN) algorithm for angular super-resolution (SR) to improve the quality of angular SR images. Firstly, to address the problem of low luminance of images captured by LF cameras, this paper uses block threshold square reinforcement (BTSR) for image luminance enhancement. Secondly, to make the reconstructed new viewpoints of higher quality, this paper improves the attention mechanism convolutional block attention module (CBAM). This paper incorporates it into a 4D dense residual network as high dimensional attention module (HDAM). HDAM generates images along two independent dimensions, spatial and channel. The HDAM generates attention maps along two independent dimensions, space and channel, which guide the network to focus on more important features for adaptive feature modification. Finally, this paper modifies the activation function to make the network perform better in the later stages of training and more suitable for LF reconstruction tasks. This paper evaluates the network on many LF data, including real-world scenes and synthetic data. The experimental results show that the improved network algorithm can achieve higher quality LF reconstruction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shin, C., Jeon, H.-G., Yoon, Y., Kweon, I.S., Kim, S. J.: EPINET: a fully-convolutional neural network using epipolar geometry for depth from light field images. In Proceedings of IEEE Conference on Computer Vision Pattern Recognition, pp. 4748–4757 (2018)
Mitra, K., Veeraraghavan, A.: Light field denoising, light field superresolution and stereo camera based refocussing using a GMM light field patch prior. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition Workshops, pp. 22–28 (2012)
Yucer, K., Sorkine-Hornung, A., Wang, O., Sorkine-Hornung, O.: Efficient 3D object segmentation from densely sampled light fields with applications to 3D reconstruction. ACM Trans. Graph. 35(3), 22:1–22:15 (2016)
Kim, C., Zimmer, H., Pritch, Y., Sorkine-Hornung, A., Gross, M.: Scene reconstruction from high spatio-angular resolution light fields. ACM Trans. Graph. 32(4), 73:1–73:12 (2013)
Wang, T.-C., Efros, A.A., Ramamoorthi, R.: Occlusion-awaredepth estimation using light-field cameras. In: Proceedings of IEEE International Conference on Computer Vision, pp. 3487–3495 (2015)
Pearson, J., Brookes, M., Dragotti, P.L.: Plenoptic layer-based modeling for image based rendering. IEEE Trans. Image Process. 22(9), 3405–3419 (2013)
Zhang, Z., Liu, Y., Dai, Q.: Light field from micro-baseline image pair. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition, pp. 3800–3809 (2015)
Zhang, F.-L., et al.: PlenoPatch: patch-based plenoptic image manipulation. IEEE Trans. Visualization Comput. Graph. 23(5), 1561–1573 (2017). https://doi.org/10.1109/TVCG.2016.2532329
Chai, J.X., Tong, X., Chan, S.C., et al.: Plenoptic sampling. In: Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, pp. 307–318 (2000)
Zhang, C., Chen, T.: Spectral analysis for sampling image-based rendering data. IEEE Trans. Circuits Syst. Video Technol. 13(11), 1038–1050 (2003)
Do, M.N., Marchand-Maillet, D., Vetterli, M.: On the bandwidth of the plenoptic function. IEEE Trans. Image Process. 21(2), 708–717 (2011)
Zhu, C.J., Yu, L.: Spectral analysis of image-based rendering data with scene geometry. Multimedia Syst. 23, 627–644 (2017)
Vagharshakyan, S., Bregovic, R., Gotchev, A.: Light field reconstruction using shearlet transform. IEEE Trans. Pattern Anal. Mach. Intell. 40(1), 133–147 (2018)
Chen, W., Zhu, C.: Spectral analysis of a surface occlusion model for image-based rendering sampling. Digital Signal Process. 130, 103697 (2022)
Yoon, Y., Jeon, H.G., Yoo, D., Lee, J.Y., So Kweon, I.: Learning a deep convolutional network for light-field image superresolution. In: Proceedings of IEEE International Conference on Computer Vision Workshops, pp. 24–32 (2015)
Flynn, J., Neulander, I., Philbin, J., Snavely, N.: DeepStereo: learning to predict new views from the world’s imagery. In: Proceedings of IEEE Conference on Computer Vision Pattern Recognition, pp. 5515–5524 (2016)
Wu, G., Liu, Y., Fang, L., Dai, Q., Chai, T.: Light field reconstruction using convolutional network on EPI and extended applications. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1681–1694 (2019)
Wu, G., Liu, Y., Dai, Q., Chai, T.: Learning sheared EPI structure for light field reconstruction. IEEE Trans. Image Process. 28(7), 3261–3273 (2019)
Wang, Y., Liu, F., Wang, Z., Hou, G., Sun, Z., Tan, T.: End-to-end view synthesis for light field imaging with Pseudo 4DCNN. In: Proceedings of European Conference on Computer Vision, pp. 333–348 (2018)
Yeung, W.F.H., Hou, J., Chen, J., Chung, Y.Y., Chen, X.: Fast light field reconstruction with deep coarse-to-fine modeling of spatial-angular clues. In: Proceedings of European Conference on Computer Vision, pp. 137–152 (2018)
Meng, N., So, H.K.H., Sun, X., et al.: High-dimensional dense residual convolutional neural network for light field reconstruction. IEEE Trans. Pattern Anal. Mach. Intell. 43(3), 873–886 (2019)
Raj, S., Lowney, M., Shah, R., Wetzstein, G.: Stanford lytro light field archive (2016). http://lightfields.stanford.edu/LF2016.html.
Honauer, K., Johannsen, O., Kondermann, D., Goldluecke, B.: A dataset and evaluation methodology for depth estimation on 4D light fields. In: Proceedings of Asian Conference on Computer Vision, pp. 19–34 (2016)
Acknowledgment
This work was supported in part by National Natural Science Foundation of China (No. 62067003), Culture and Art Science Planning Project of Jiangxi Province (No. YG2018042), Humanities and Social Science Project of Jiangxi Province (No.JC18224).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Liu, Q., Li, R., Yan, K., Wang, Y., Luo, Y. (2024). An Improved 4D Convolutional Neural Network for Light Field Reconstruction. In: Wu, C., Chen, X., Feng, J., Wu, Z. (eds) Mobile Networks and Management. MONAMI 2023. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 559. Springer, Cham. https://doi.org/10.1007/978-3-031-55471-1_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-55471-1_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-55470-4
Online ISBN: 978-3-031-55471-1
eBook Packages: Computer ScienceComputer Science (R0)