Phase-based learning for micro-baseline depth estimation

Methods designed for traditional stereo matching problem are not suitable for micro-baseline stereo problem. In this paper, a novel phase-based learning framework is proposed dedicated to this problem. The inspiration comes from the relationship between phase in frequency domain and shifts in space domain. Steerable pyramid decomposition is used to compute the phase difference of micro-baseline stereo inputs, and learning based methods are adopted to determine disparity from phase difference patch. The proposed framework is a combination of domain transformation and machine learning, which exploits neighbor gradient information as well as data-driven benefits. Experimental results show that the combination effectively reduces the inherent error of phase-based methods, and our innovative framework outperforms traditional stereo matching methods.

[1]  Cheng Zhang,et al.  Accurate Image-Guided Stereo Matching With Efficient Matching Cost and Disparity Refinement , 2016, IEEE Transactions on Circuits and Systems for Video Technology.

[2]  Max Grosse,et al.  Phase-based frame interpolation for video , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Jian Sun,et al.  Face Alignment at 3000 FPS via Regressing Local Binary Features , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Bastian Goldlücke,et al.  A Dataset and Evaluation Methodology for Depth Estimation on 4D Light Fields , 2016, ACCV.

[5]  William T. Freeman,et al.  Presented at: 2nd Annual IEEE International Conference on Image , 1995 .

[6]  Hongyang Chao,et al.  MeshStereo: A Global Stereo Model with Mesh Alignment Regularization for View Interpolation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[7]  Frédo Durand,et al.  Phase-based video motion processing , 2013, ACM Trans. Graph..

[8]  Yann LeCun,et al.  Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches , 2015, J. Mach. Learn. Res..

[9]  Ce Liu,et al.  Deep Convolutional Neural Network for Image Deconvolution , 2014, NIPS.

[10]  Dongxiao Li,et al.  Accurate RGB camera relocalization using regression forest , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[11]  Carsten Rother,et al.  Fast cost-volume filtering for visual correspondence and beyond , 2011, CVPR 2011.

[12]  C. D. Kuglin,et al.  The phase correlation image alignment method , 1975 .

[13]  Kyoung Mu Lee,et al.  Accurate Image Super-Resolution Using Very Deep Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Qionghai Dai,et al.  Light field from micro-baseline image pair , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Jian Guo Liu,et al.  The Illumination Robustness of Phase Correlation for Image Alignment , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.