Depth estimation improvement in 3D integral imaging using an edge removal approach
- 38 Downloads
A new depth estimation method for 3D reconstruction in a synthetic aperture integral imaging framework is presented. This method removes the edges of the objects in the elemental images when the objects are in focus. This strategy aims to compensate for the noise that objects focused close to the cameras can introduce into the photo-consistency measure of objects at higher depths. Furthermore, a photo-consistency criterion is applied combining a defocus and a correspondence measure, and a depth regularization method which smooths noisy depth results for the case of object surfaces. The proposed method obtains consistent results for any type of object surfaces as well as very sharp boundaries. Experimental results show that our method reduces the noise in the object edges and gives rise to an improvement in the depth map results in relation to the other methods shown in the comparative analysis.
KeywordsIntegral imaging Depth map Removal edges Defocus Regularisation
This work was supported by the Spanish Ministry of Economy and Competitiveness (MINECO) under the Projects SEOSAT (ESP2013-48458-C4-3- P) and MTM2013-48371-C2-2-PDGI, by the Generalitat Valenciana through the Project PROMETEO-II-2014-062, and by the University Jaume I through the Project UJIP11B2014-09. B. Javidi would like to acknowledge support under NSF/IIS-1422179 and ONR under N00014-17-1-2561.
- 1.Lytro redefines photography with light field cameras. Press release. (2011) (Outline). https://www.lytro.com/
- 4.Azevedo TCS, Tavares JMRS, Vaz MAP (2009) 3d object reconstruction from uncalibrated images using and off-the-shelf camera. In: Tavares J, Jorge RN (eds) Advances in computational vision and medical image processing: methods and applications. Springer, BerlinGoogle Scholar
- 6.Bae S, Duran F (2007) Defocus magnification. Eurographics 26(3):571–579Google Scholar
- 14.Espinós-Morató H, Latorre-Carmona P, Sotoca JM, Pla F, Javidi B (2017) Combining defocus and photoconsistency for depth map estimation in 3D integral imaging. In: 8th Iberian conference on pattern recognition and image analysis (IbPRIA), pp 114–121Google Scholar
- 22.Javidi B, Okano F, Son JY (2008) Three-dimensional imaging, visualization, and display technology. Springer, BerlinGoogle Scholar
- 27.Martínez-Uso A, Latorre-Carmona P, Sotoca JM, Pla F, Javidi B (2016) Depth estimation in integral imaging based on a maximum voting strategy. IEEE J Display Technol 12(12):1715–1723Google Scholar
- 35.Sokolov AP (1911) Autostereoscopy and integral photography by professor Lippmann’s method. Moscow State University Press, MoscowGoogle Scholar