Abstract
High angular resolution light field (LF) enables exciting applications such as depth estimation, virtual reality, and augmented reality. Although many light field angular super-resolution methods have been proposed, the reconstruction problem of LF with a wide-baseline is far from being solved. In this paper, we propose an end-to-end learning-based approach to achieve angular super-resolution of the light field with a wide-baseline. Our model consists of three components. We first train a convolutional neural network to predict the depth map for each sub-aperture view. Then the estimated depth maps are used to warp the input views. In the final component, we first use a convolutional neural network to fuse the initial warped light fields, and then we propose an edge-aware inpainting network to modify the inaccurate pixels in the near-edge regions. Accordingly, we design an EdgePyramid structure that contains multi-scale edges to perform the inpainting of near-edge pixels. Moreover, we introduce a novel loss function to reduce the artifacts and further estimate the similarity in near-edge regions. Experimental results on various light field datasets including large-baseline light field images show that our method outperforms the state-of-the-art light field angular super-resolution methods, especially in the terms of visual performance near edges.
Similar content being viewed by others
References
Lytro. https://www.lytro.com/ (2016)
Raytrix. https://www.raytrix.de/ (2016)
Chao, D., Chen, C.L., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: European Conference on Computer Vision (ECCV), pp. 184–199 (2014)
Chaurasia, G., Sorkine, O., Drettakis, G.: Silhouette-aware warping for image-based rendering. Comput. Graph. Forum 4, 1223–1232 (2011)
Couillaud, J., Ziou, D.: Light field variational estimation using a light field formation model. Vis. Comput. 36, 237–251 (2020)
Chaurasia, G., Duchene, S., Sorkine-Hornung, O., Drettakis, G.: Depth synthesis and local warps for plausible image-based navigation. ACM Trans. Graph. (TOG) 32(3), 30:1–30:12 (2013)
Habtegebrial, T., Varanasi, K., Bailer, C., Stricker, D.: Fast view synthesis with deep stereo vision. arXiv:1804.09690 (2018)
Honauer, K., Johannsen, O., Kondermann, D., Goldluecke, B.: A dataset and evaluation methodology for depth estimation on 4d light fields. In: Asian Conference on Computer Vision (2016)
Jin, J., Hou, J., Yuan, H., Kwong, S.: Learning light field angular super-resolution via a geometry-aware network. In: Association for the Advance of Artificial Intelligence (AAAI) (2020)
Kalantari, N.K., Wang, T.C., Ravi, R.: Learning-based view synthesis for light field cameras. ACM Trans. Graph. (SIGGRAPH Asia) 35(6), 193:1–193:10 (2016)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. (NeurIPS) 2, 1097–1105 (2012)
Levoy, M., Hanrahan, P.: Light field rendering. In: Siggraph, pp. 31–42 (1996)
Liu, Y., Dai, Q., Xu, W.: A real time interactive dynamic light field transmission system. In: IEEE International Conference on Multimedia and Expo (2006)
Min, X., Zhou, J., Zhai, G., Callet, P.L., Yang, X., Guan, X.: A metric for light field reconstruction, compression, and display quality evaluation. IEEE Trans. Image Process. 29, 3790–3804 (2020)
Mitra, K., Veeraraghavan, A.: Light field denoising, light field superresolution and stereo camera based refocussing using a GMM light field patch prior. In: Computer Vision and Pattern Recognition Workshops (CVPR) (2012)
Pearson, J., Brookes, M., Dragotti, P.L.: Plenoptic layer-based modeling for image based rendering. IEEE Trans. Image Process A Publ. IEEE Signal Process. Soc. 9, 3405–3419 (2013)
Schilling, H., Diebold, M., Rother, C., Jahne, B.: Trust your model: light field depth estimation with inline occlusion handling. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Shi, J., Jiang, X., Guillemot, C.: A framework for learning depth from a flexible subset of dense and sparse light field views. IEEE Trans. Image Process. 99, 1–15 (2019)
Shi, L., Hassanieh, H., Davis, A., Katabi, D., Durand, F.: Light field reconstruction using sparsity in the continuous Fourier domain. ACM Trans. Graph. 1, 1–13 (2014)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proc. ICLR (2015)
Srinivasan, P.P., Wang, T., Sreelal, A., Ramamoorthi, R., Ng, R.: Learning to synthesize a 4d RGBD light field from a single image. In: International Conference on Computer Vision (ICCV), pp. 1–9 (2017)
Vadathya, A.K., Girish, S., Mitra, K.: A deep learning framework for light field reconstruction from focus-defocus pair: a minimal hardware approach. In: Computational Cameras and Displays (CCD) workshop (CVPRW) (2018)
Vagharshakyan, S., Bregovic, R., Gotchev, A.: Light field reconstruction using Shearlet transform. IEEE Trans. Pattern Anal. Mach. Intell. 1, 133–147 (2018)
Vaish, V., Adams, A.: The (new) Stanford light field archive. http://lightfield.stanford.edu/acq.html (2018)
Wang, T.C., Efros, A.A., Ramamoorthi, R.: Occlusion-aware depth estimation using light-field cameras. In: IEEE International Conference on Computer Vision (2016)
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: European Conference on Computer Vision (ECCV), pp. 1–16 (2018)
Wang, Y., Liu, F., Zhang, K., Wang, Z., Tan, T.: High-fidelity view synthesis for light field imaging with extended pseudo 4DCNN. IEEE Trans. Comput. Imaging 99, 1 (2020)
Wanner, S., Goldluecke, B.: Variational light field analysis for disparity estimation and super-resolution. IEEE Trans. Pattern Anal. Mach. Intell. 36(3), 1 (2013)
Wanner, S., Meister, S., Goldlücke, B.: Datasets and Benchmarks for Densely Sampled 4D Light Fields. The Eurographics Association (2013)
Wetzstein, G.: MIT synthetic light field archive. https://web.media.mit.edu/~gordonw/SyntheticLightFields/index.php (2013)
Wilburn, B., Joshi, N., Vaish, V., Talvala, E.V., Antunez, E., Barth, A., Adams, A., Horowitz, M., Levoy, M.: High performance imaging using large camera arrays. ACM Trans. Graph. 3, 765–776 (2005)
Wu, G., Liu, Y., Fang, L., Chai, T.: Lapepi-net: a Laplacian pyramid EPI structure for learning-based dense light field reconstruction. arXiv:1902.06221 (2019)
Wu, G., Zhao, M., Wang, L., Dai, Q., Liu, Y.: Light field reconstruction using deep convolutional network on EPI. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Wu, Y., Wang, Y., Liang, J., Baji, I.V., Wang, A.: Light field all-in-focus image fusion based on spatially-guided angular information. J. Vis. Commun. Image Represent. 72, 102878 (2020)
Yoon, Y., Jeon, H.G., Yoo, D., Lee, J.Y., Kweon, I.S.: Learning a deep convolutional network for light-field image super-resolution. In: IEEE International Conference on Computer Vision Work-shop (ICCVW), pp. 1–9 (2015)
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. 6, 848–852 (2017)
Zhang, Z., Liu, Y., Dai, Q.: Light field from micro-baseline image pair. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Zheng, H., Ji, M., Wang, H., Liu, Y., Fang, L.: Crossnet: an end-to-end reference-based super resolution network using cross-scale warping. In: European Conference on Computer Vision (ECCV) (2018)
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Funding
This work was supported in part by the Science and Technology Plan Project of Sichuan Province under Grant 2021YFG0350, in part by the National Key Research and Development Program of China under Grant 2016YFB0700802, and in part by the Innovative Youth Fund Program of the State Oceanic Administration of China under Grant 2015001.
Conflict of interest
The authors have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This work was supported in part by the Science and Technology Plan Project of Sichuan Province under Grant 2021YFG0350, in part by the National Key Research and Development Program of China under Grant 2016YFB0700802, and in part by the Innovative Youth Fund Program of the State Oceanic Administration of China under Grant 2015001.
Rights and permissions
About this article
Cite this article
Liu, X., Wang, M., Wang, A. et al. Depth-guided learning light field angular super-resolution with edge-aware inpainting. Vis Comput 38, 2839–2851 (2022). https://doi.org/10.1007/s00371-021-02159-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-021-02159-6