Abstract
Light field photography captures rich structural information that may facilitate a number of traditional image processing and computer vision tasks. A crucial ingredient in such endeavors is accurate depth recovery. We present a novel framework that allows the recovery of a high quality continuous depth map from light field data. To this end we propose a generative model of a light field that is fully parametrized by its corresponding depth map. The model allows for the integration of powerful regularization techniques such as a non-local means prior, facilitating accurate depth map estimation. Comparisons with previous methods show that we are able to recover faithful depth maps with much finer details. In a number of challenging real-world examples we demonstrate both the effectiveness and robustness of our approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We discuss the implication of the no-occlusion assumption in more detail in the supplemental material.
- 2.
We use the given default values \(\sigma =1.0\) and \(\tau =0.5\).
- 3.
- 4.
- 5.
The images have neither been gamma compressed nor rectified.
- 6.
Buddha, buddha2, horses, medieval, monasRoom, papillon, stillLife.
References
The (new) stanford light field archive (2008). http://lightfield.stanford.edu. Accessed 07 Apr 2016
Adelson, E.H., Wang, J.Y.A.: Single lens stereo with a plenoptic camera. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 14(2), 99–106 (1992)
Bishop, T.E., Favaro, P.: The light field camera: extended depth of field, aliasing, and superresolution. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 34(5), 972–986 (2012)
Bolles, R.C., Baker, H.H., Marimont, D.H.: Epipolar-plane image analysis: an approach to determining structure from motion. Int. J. Comput. Vis. 1(1), 7–55 (1987)
Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: CVPR (2005)
Carbonetto, P.: A programming interface for L-BFGS-B in MATLAB (2014). https://github.com/pcarbo/lbfgsb-matlab. Accessed 15 Apr 2015
Chai, J.X., Tong, X., Chan, S.C., Shum, H.Y.: Plenoptic sampling. In: ACM SIGGRAPH (2000)
Cho, D., Kim, S., Tai, Y.-W.: Consistent matting for light field images. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part IV. LNCS, vol. 8692, pp. 90–104. Springer, Heidelberg (2014)
Dansereau, D.G., Bongiorno, D.L., Pizarro, O., Williams, S.B.: Light field image denoising using a linear 4D frequency-hyperfan all-in-focus filter. In: IS&T/SPIE Electronic Imaging (2013)
Dansereau, D.G., Mahon, I., Pizarro, O., Williams, S.B.: Plenoptic flow: closed-form visual odometry for light field cameras. In: IROS (2011)
Dansereau, D.G., Pizarro, O., Williams, S.B.: Decoding, calibration and rectification for lenselet-based plenoptic cameras. In: CVPR (2013)
Diebold, M., Goldlücke, B.: Epipolar plane image refocusing for improved depth estimation and occlusion handling. In: Annual Workshop on Vision, Modeling and Visualization: VMV (2013)
Favaro, P.: Recovering thin structures via nonlocal-means regularization with application to depth from defocus. In: CVPR (2010)
Ferstl, D., Reinbacher, C., Ranftl, R., Rüther, M., Bischof, H.: Image guided depth upsampling using anisotropic total generalized variation. In: ICCV (2013)
Goldluecke, B., Wanner, S.: The variational structure of disparity and regularization of 4D light fields. In: CVPR (2013)
Gortler, S.J., Grzeszczuk, R., Szeliski, R., Cohen, M.F.: The lumigraph. In: ACM SIGGRAPH (1996)
Heber, S., Pock, T.: Shape from light field meets robust PCA. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VI. LNCS, vol. 8694, pp. 751–767. Springer, Heidelberg (2014)
Heber, S., Ranftl, R., Pock, T.: Variational shape from light field. In: Heyden, A., Kahl, F., Olsson, C., Oskarsson, M., Tai, X.-C. (eds.) EMMCVPR 2013. LNCS, vol. 8081, pp. 66–79. Springer, Heidelberg (2013)
Isaksen, A., McMillan, L., Gortler, S.J.: Dynamically reparameterized light fields. In: ACM SIGGRAPH. ACM (1996)
Kim, C., Zimmer, H., Pritch, Y., Sorkine-Hornung, A., Gross, M.H.: Scene reconstruction from high spatio-angular resolution light fields. ACM SIGGRAPH (2013)
Levoy, M., Hanrahan, P.: Light field rendering. In: ACM SIGGRAPH. ACM (1996)
Li, N., Ye, J., Ji, Y., Ling, H., Yu, J.: Saliency detection on light field. In: CVPR (2014)
Liang, C.K., Lin, T.H., Wong, B.Y., Liu, C., Chen, H.H.: Programmable aperture photography: multiplexed light field acquisition. ACM SIGGRAPH (2008)
Lin, H., Chen, C., Bing Kang, S., Yu, J.: Depth recovery from light field using focal stack symmetry. In: ICCV (2015)
Ng, R.: Digital light field photography. Ph.D. thesis, stanford university (2006). Ren Ng founded Lytro
Ng, R., Levoy, M., Brédif, M., Duval, G., Horowitz, M., Hanrahan, P.: Light field photography with a hand-held plenoptic camera. Computer Science Technical Report CSTR 2(11) (2005)
Park, J., Kim, H., Tai, Y.W., Brown, M.S., Kweon, I.: High quality depth map upsampling for 3D-TOF cameras. In: ICCV (2011)
Perwass, C., Wietzke, L.: The next generation of photography (2010). https://github.com/pcarbo/lbfgsb-matlab. Accessed 15 Apr 2015, Perwass and Wietzke founded Raytrix
Perwass, C., Wietzke, L.: Single lens 3D-camera with extended depth-of-field. In: IS&T/SPIE Electronic Imaging (2012)
Sebe, I.O., Ramanathan, P., Girod, B.: Multi-view geometry estimation for light field compression. In: Annual Workshop on Vision, Modeling and Visualization: VMV (2002)
Sun, D., Roth, S., Black, M.J.: Secrets of optical flow estimation and their principles. In: CVPR (2010)
Tao, M.W., Hadap, S., Malik, J., Ramamoorthi, R.: Depth from combining defocus and correspondence using light-field cameras. In: ICCV (2013)
Tosic, I., Berkner, K.: Light field scale-depth space transform for dense depth estimation. In: CVPR Workshops (2014)
Vaish, V., Wilburn, B., Joshi, N., Levoy, M.: Using plane + parallax for calibrating dense camera arrays. In: CVPR (2004)
Wang, T.C., Efros, A.A., Ramamoorthi, R.: Occlusion-aware depth estimation using light-field cameras. In: ICCV (2015)
Wanner, S., Goldluecke, B.: Globally consistent depth labeling of 4D light fields. In: CVPR (2012)
Wanner, S., Goldluecke, B.: Spatial and angular variational super-resolution of 4D light fields. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 608–621. Springer, Heidelberg (2012)
Wanner, S., Goldluecke, B.: Variational light field analysis for disparity estimation and super-resolution. IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 36(3), 606–619 (2014)
Wanner, S., Meister, S., Goldluecke, B.: Datasets and benchmarks for densely sampled 4D light fields. In: Annual Workshop on Vision, Modeling and Visualization: VMV (2013)
Wanner, S., Straehle, C., Goldluecke, B.: Globally consistent multi-label assignment on the ray space of 4D light fields. In: CVPR (2013)
Zhang, Z., Liu, Y., Dai, Q.: Light field from micro-baseline image pair. In: CVPR (2015)
Zhu, C., Byrd, R.H., Lu, P., Nocedal, J.: Algorithm 778: L-BFGS-B: fortran subroutines for large-scale bound-constrained optimization. ACM TOMS 23(4), 550–560 (1997)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Sajjadi, M.S.M., Köhler, R., Schölkopf, B., Hirsch, M. (2016). Depth Estimation Through a Generative Model of Light Field Synthesis. In: Rosenhahn, B., Andres, B. (eds) Pattern Recognition. GCPR 2016. Lecture Notes in Computer Science(), vol 9796. Springer, Cham. https://doi.org/10.1007/978-3-319-45886-1_35
Download citation
DOI: https://doi.org/10.1007/978-3-319-45886-1_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-45885-4
Online ISBN: 978-3-319-45886-1
eBook Packages: Computer ScienceComputer Science (R0)