A depth estimating method from a single image using FoE CRF
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.
KeywordsField of experts (FoE) Conditional random field (CRF) Non-stationary spatially variance Minimum mean square error (MMSE)
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).
- 1.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 recognitionGoogle Scholar
- 5.Huang J, Lee A, Mumford D (2000) Statistics of range images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 324–331Google Scholar
- 6.Karsch K, Liu C, Kang SB (2012) Depth extraction from video using non-parametric sampling. In: Proceedings of the 12th European conference on computer visionGoogle Scholar
- 7.Lafferty J, McCallum A, Pereira F (2001) Conditional random fields: probabilistic models for segmenting and labeling sequence data. International conference on machine learning (ICML)Google Scholar
- 8.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 systemsGoogle Scholar
- 9.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 recognitionGoogle Scholar
- 11.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 processingGoogle Scholar
- 13.Sakuragi K, Kawanaka A (2010) Depth estimation from stereo images using sparsity. In: Proceedings of the international conference on signal processingGoogle Scholar
- 16.Saxena A, Chung SH, Ng AY (2005) Learning depth from single monocular images. In: Proceedings of advances in neural information processing systemsGoogle Scholar
- 17.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 recognitionGoogle Scholar
- 19.Yang Q (2012) A non-Local cost aggregation method for stereo matching. In: Proceedings of the IEEE conference on computer vision and pattern recognitionGoogle Scholar