Abstract
With increasing demands of three-dimensional (3D) contents, the conversion of many two-dimensional (2D) contents to 3D contents has become a focus in 3D image processing. The most important and difficult problem in 2D-to-3D conversion is the estimation of the depth map using only a single-view image. Therefore, a novel method for estimating a depth map for stereoscopic conversion is proposed in this paper. A simulated haze image generated by adding a haze veil on the input image is used to represent salient region segmentation. The 3D stereoscopic image is generated on the basis of the depth map estimated by the haze removal algorithm without any heuristic cues or user interaction. A comparative study and quantitative evaluation with some other state of the art conversion methods are carried out, which demonstrate that using the proposed approach, similar or better-quality results may be obtained.
Similar content being viewed by others
References
W. J. Tam and L. Zhang: Proc. ICME, 2006, p. 1869.
S. Battiato, S. Curti, E. Scordato, M. Tortora, and M. La Cascia: Three-Dimensional Image Capture and Applications V1 5302 (2004) 95.
D. Hoiem, A. A. Efros, and M. Hebert: Proc. ACM SIGGRAPH, 2005, p. 577.
J. Park and C. Kim: Proc. SPIE VCIP, 2006, p. 60771O–1.
Y.-M. Tsai, Y.-L. Chang, and L.-G. Chen: Proc. Intl. Symp. Intelligent Signal Proc. and Comm. Syst., 2006, p. 586.
Y. J. Jung, A. Baik, J. Kim, and D. Park: Proc. SPIE — Int. Soc. Opt. Eng., 2009, p. 72371U–1.
H. Murata, Y. Mori, S. Yamashita, A. Maenaka, S. Okada, K. Oyamada, and S. Kishimoto: Proc. SID Digest of Technical Papers 32.2, 1998, p. 919.
K. Han and K. Hong: Proc. ICCE, 2011, p. 651.
C.-C. Cheng, C.-T. Li, and L.-G. Chen: IEEE Trans. Consum. Electron. 56 (2010) 1739.
N.-E. Yang, J. W. Lee, and R.-H. Park: Proc. ICCE, 2012, p. 311.
A. Saxena, S. H. Chung, and A. Y. Ng: Proc. NIPS, 2005, p. 1161.
A. Saxena, S. H. Chung, and A. Y. Ng: Int. J. Comput. Vis. 76 (2008) 53.
K. M. He, J. Sun, and X. O. Tang: Proc. CVPR, 2009, p. 1956.
K. He, J. Sun, and X. Tang: IEEE Trans. Pattern Anal. Mach. Intell. 33 (2011) 2341.
E. H. Land: Proc. Natl. Acad. Sci. U.S.A. 83 (1986) 3078.
N. Hautiére, J.-P. Tarel, J. Lavenant, and D. Aubert: Mach. Vision Appl. 17 (2006) 8.
K. M. He, J. Sun, and X. O. Tang: Proc. ECCV, 2010, p. 1.
D. Sun, S. Roth, and M. J. Black: Proc. CVPR, 2010, p. 1.
Make3D Laser+Image data (Dataset-2): http://make3d.cs.cornell.edu/data.html.
C. L. Zitnick, S. B. Kang, M. Uyttendaele, S. Winder, and R. Szeliski: ACM Trans. Graph. 23 (2004) 600.
ITU-R Recommendation BT.500-10, (2000).
W. J. Tam, F. Speranza, S. Yano, K. Shimono, and H. Ono: IEEE Trans. Broadcast 57 (2011) 335.
M. van Rossum and Th. Nieuwenhuizen: Rev. Mod. Phys. 71 (1999) 313.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Guo, F., Tang, J. & Peng, H. Adaptive estimation of depth map for two-dimensional to three-dimensional stereoscopic conversion. OPT REV 21, 60–73 (2014). https://doi.org/10.1007/s10043-014-0010-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10043-014-0010-4