Abstract
A high-order conditional random field (CRF) for depth estimation from a single image is proposed in this paper. Instead of formulating the problem with the Guassian or Laplacian CRF modeling techniques, which cannot exploit the full potential offered by the probabilistic modeling, this paper proposes a depth estimation CRF model with field of experts (FoE) as the prior. The minimum mean square error (MMSE) criteria is used to infer depth. Moreover, it is assumed that the variance of depth estimation error varies spatially in depth estimation model. This allows the proposed method to enjoy the benefits offered by the flexible prior and have the advantages of making use of the non-stationary variance probability model. Experimental results indicate that the proposed method outperforms state-of-the-art approaches in terms of RMSE-error and log10-error.
Similar content being viewed by others
References
Batra D, Saxena A (2012) Learning the right model: efficient max-margin learning in laplacian CRFs. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Felzenszwalb P, Huttenlocher D (2004) Efficient graph-based image segmentation. Int J Comput Vision 59(2):167181
Hinton GE (2002) Training products of experts by minimizing contrastive divergence. Neural Comput 14(8):1771–1800
Hoiem D, Efros A, Hebert M (2007) Recovering surface layout from an image. Int J Comput Vision 75(1):151–172
Huang J, Lee A, Mumford D (2000) Statistics of range images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 324–331
Karsch K, Liu C, Kang SB (2012) Depth extraction from video using non-parametric sampling. In: Proceedings of the 12th European conference on computer vision
Lafferty J, McCallum A, Pereira F (2001) Conditional random fields: probabilistic models for segmenting and labeling sequence data. International conference on machine learning (ICML)
Li C, Saxena A, Chen T (2011) 𝜃-mrf: capturing spatial and semantic structure in the parameters for scene understanding. In: Proceedings of advances in neural information processing systems
Liu B, Gould S, Koller D (2010) Single image depth estimation from predicted semantic labels. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Portilla J, Strela V, Wainwright M, Sinmoncelli E (2003) Image denoising using scale mixtures of gaussians in the wavelet domain. IEEE Trans Image Process 12(11):1338–1351
Ranipa K, Joshi M (2011) A practical approach for depth estimation and image restoration using defocus cue. In: Proceedings of the IEEE machine learning for signal processing
Roth S, Black MJ (2009) Fields of experts. Int J Comput Vision 82(2):205–229
Sakuragi K, Kawanaka A (2010) Depth estimation from stereo images using sparsity. In: Proceedings of the international conference on signal processing
Saxena A, Sun M, Ng AY (2009) Make3d: learning 3D scene structure from a single still image. IEEE Trans Pattern Anal Mach Intell 31(5):824–840
Saxena A, Chung SH, Ng AY (2008) 3-d depth reconstruction from a single still image. Int J Comput Vision 76(1):53–69
Saxena A, Chung SH, Ng AY (2005) Learning depth from single monocular images. In: Proceedings of advances in neural information processing systems
Schmidt U, Gao Q, Roth S (2010) A generative perspective on MRFs in low-level vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Tŏsić I, Olshausen B, Culpepper B (2011) Learning sparse representations of depth. IEEE J Sel Top Sig Process 5(5):941–952
Yang Q (2012) A non-Local cost aggregation method for stereo matching. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Zhang H, Zhang Y, Li H, Huang T (2012) Generative bayesian image super resolution with natural image prior. IEEE Trans Sig Process 21(9):4054–4067
Acknowledgments
This work is supported by the National Natural Science Foundation of China under Grant 60932007, by National 863 Programm (No. 2012AA03A301), and by Ph.D. Programs Foundation of Ministry of Education of China (No. 20110032110029).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, X., Hou, C., Pu, L. et al. A depth estimating method from a single image using FoE CRF. Multimed Tools Appl 74, 9491–9506 (2015). https://doi.org/10.1007/s11042-014-2130-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-014-2130-z