Abstract
Depth estimation based on light field imaging is a new way of depth estimation. The abundant data of light field paves the way for deep learning methods to play a role. In recent years, deep convolutional neural network (CNN) has shown great advantages in extracting image texture features. Inspired by this, we design a deep CNN with EPI synthetic images as input for depth estimation, which is called EENet. Under the constrains of epipolar geometry, pixels corresponding to a common object point are distributed in a straight line in the epipolar plane image (EPI), and the EPI synthetic image is easier to extract features by convolution kernel. Our EENet has the structure characteristics of multi-stream inputs and skip connections. Specifically, the horizontal EPI synthetic image, the vertical EPI synthetic image and the central view image are first generated from the light field, and input into the three streams of EENet respectively. Next, the U-shaped neural network is designed to predict the depth information, that is, the convolution and pooling blocks are used to encode the features, while the deconvolution layer and convolution layer are combined to decode features and recover the depth information. Furthermore, we employ skip connections between the encoding layers and the decoding layers to fuse the shallow location features and deep semantic features. Our EENet is trained and tested on the light field benchmark, and has obtained good experimental results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Liu, F., Hou, G., Sun, Z., et al.: High quality depth map estimation of object surface from light-field image. Neurocomputing 252(252), 3–16 (2017)
Liu, F., Shen, C., Lin, G., et al.: Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2024–2039 (2015)
Kim, C., Zimmer, H., Pritch, Y., et al.: Scene reconstruction from high spatio-angular resolution light fields. ACM Trans. Graph. 32(4), 73:1–73:12 (2013)
Shin, C., Jeon, H.G., Yoon, Y., et al.: Epinet: a fully-convolutional neural network using epipolar geometry for depth from light field images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4748–4757 (2018)
Tao, M.W., Hadap, S., Malik, J., et al.: Depth from combining defocus and correspondence using light-field cameras. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 673–680 (2013)
Mun, J.H., Ho, Y.S.: Occlusion aware reduced angular candidates based light field depth estimation from an epipolar plane image. Electron. Imaging 2018(13), 390-1–390-6 (2018)
Han, Q., Jung, C.: Guided filtering based data fusion for light field depth estimation with L0 gradient minimization. J. Vis. Commun. Image Represent. 55, 449–456 (2018)
Mishiba, K.: Fast depth estimation for light field cameras. IEEE Trans. Image Process. 29, 4232–4242 (2020)
Wanner, S., Goldluecke, B.: Globally consistent depth labeling of 4D light fields. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 41–48. IEEE (2012)
Jeon, H.G., Park, J., Choe, G., et al.: Accurate depth map estimation from a lenslet light field camera. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1547–1555 (2015)
Neri, A., Carli, M., Battisti, F.: A maximum likelihood approach for depth field estimation based on epipolar plane images. IEEE Trans. Image Process. 28(2), 827–840 (2018)
Lourenco, R., Assuncao, P., Tavora, L.M., et al.: Silhouette enhancement in light field disparity estimation using the structure tensor. In: International Conference on Image Processing, pp. 2580–2584 (2018)
Li, J., Jin, X.: EPI-neighborhood distribution based light field depth estimation. In: ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2003–2007. IEEE (2020)
Schilling, H., Diebold, M., Rother, C., et al.: Trust your model: light field depth estimation with inline occlusion handling. In: Computer Vision Pattern Recognition, pp. 4530–4538 (2018)
Heber, S., Pock, T.: Convolutional networks for shape from light field. In: Computer Vision and Pattern Recognition, pp. 3746–3754 (2016)
Guo, C., Jin, J., Hou, J., et al.: Accurate light field depth estimation via an occlusion-aware network. In: 2020 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6. IEEE (2020)
Johannsen, O., Sulc, A., Goldluecke, B.: What sparse light field coding reveals about scene structure. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3262–3270 (2016)
Heber, S., Yu, W., Pock, T.: Neural EPI-volume networks for shape from light field. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2252–2260 (2017)
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. 28(12), 5867–5880 (2019)
Long, J., Shelhamer, E., Darrell, T., et al.: Fully convolutional networks for semantic segmentation. In: Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Honauer, K., Johannsen, O., Kondermann, D., Goldluecke, B.: A dataset and evaluation methodology for depth estimation on 4D light fields. In: Lai, S.-H., Lepetit, V., Nishino, Ko., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10113, pp. 19–34. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-54187-7_2
Acknowledgment
This work has been supported by Natural Science Foundation of Nanjing Institute of Technology (Grant Nos. CKJB201804, ZKJ201906), National Natural Science Foundation of China (Grant No. 62076122) the Jiangsu Specially-Appointed Professor Program, the Talent Startup project of NJIT (No. YKJ201982), Science and Technology Innovation Project of Nanjing for Oversea Scientist.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Han, L., Huang, X., Shi, Z., Zheng, S. (2021). Learning Depth from Light Field via Deep Convolutional Neural Network. In: Tian, Y., Ma, T., Khan, M.K. (eds) Big Data and Security. ICBDS 2020. Communications in Computer and Information Science, vol 1415. Springer, Singapore. https://doi.org/10.1007/978-981-16-3150-4_40
Download citation
DOI: https://doi.org/10.1007/978-981-16-3150-4_40
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-3149-8
Online ISBN: 978-981-16-3150-4
eBook Packages: Computer ScienceComputer Science (R0)