Abstract
Depth recovery for single image is very important to 2D-3D image conversion, which is a challenging problem in computer vision. The focus-defocus as an effective pictorial cue, has been paid more and more attention. In this paper, we reveal the relationship between entropy of DCT coefficient and scale parameter of PSF. Then, a new method to depth recovery for single images using focus-defocus cue is proposed, in which the entropy of DCT coefficient is regarded as the measure of blur, and linear operation mapping the level of blur to depth is adopted. The proposed method, which can generate pixel-level depth map, is unnecessary to select threshold. The experimental results indicate that the new method is reliable and effective.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Fehn, C.: A 3D-TV approach using depth-image-based rendering (DIBR). In: Image Process, pp. 482–487 (2003)
Liu, Y., Wang, J., Zhang, H.: Depth image-based temporal error concealment for 3-D video transmission. Circuits Syst. Video Technol. 20, 600–604 (2010)
Zhang, L., Knorr, S.: 3D-TV content creation: automatic 2D-to-3D video conversion. Broadcasting 1–12 (2011)
Gokstorp, M.: Computing depth from out-of-focus blur using a local frequency representation. In: Pattern Recognition-Conference A: Computer Vision & Image Processing, vol. 1, pp. 153–158 (1994)
Rayala, J., Gupta, S., Mullick, S.K.: Estimation of depth from defocus as polynomial system identification. Image Signal Process. 148, 356–362 (2001)
Mendapara, P., Minhas, R., Wu, Q.M.J.: Depth map estimation using exponentially decaying focus measure based on SUSAN operator. In: Systems, Man and Cybernetics, pp. 3705–3708 (2009)
Paramanand, C., Rajagopalan, A.N.: Depth from motion and optical blur with an unscented Kalman filter. IEEE Trans. Image Process. 21, 2798–2811 (2012)
Lin, X., Suo, J., Dai, Q.: Extracting depth and radiance from a defocused video pair. IEEE J. Mag. 25(4), 557–569 (2016)
Xiao, J., Liu, T., Zhang, Y., Zou, B., Lei, J., Li, Q.: Multi-focus image fusion based on depth extraction with inhomogeneous diffusion equation. Signal Process. 14(1), 1–30 (2016)
Valenecia, S.A., Rodriguez-Dagnino, R.M.: Synthesizing stereo 3D views from focus cues in monoscopic 2D images. In: Proceedings of SPIE-IS&T Electronic Imaging, vol. 5006, pp. 377–388 (2003)
Acknowledgement
This work is supported by the Harbin Science and Technology Bureau outstanding subject leader fund project (2017RAXXJ055), and Nature Science Foundation of Heilongjiang Province (F2018020).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Sun, H., Zhao, Z., Han, X., Zhang, L. (2019). Depth Recovery from Focus-Defocus Cue by Entropy of DCT Coefficient. In: Jia, M., Guo, Q., Meng, W. (eds) Wireless and Satellite Systems. WiSATS 2019. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 281. Springer, Cham. https://doi.org/10.1007/978-3-030-19156-6_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-19156-6_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19155-9
Online ISBN: 978-3-030-19156-6
eBook Packages: Computer ScienceComputer Science (R0)