Sped-up PatchMatch Belief Propagation (SPM-BP)
This is an implementation of SPM-BP for Optical Flow estimation that correspondes to our published paper:
Y. Li, D. Min, M. S. Brown, M. N. Do, J. Lu. "SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs". in ICCV 2015.
Project Website: [Efficient Inference for Continuous MRFs] (https://publish.illinois.edu/visual-modeling-and-analytics/efficient-inference-for-continuous-mrfs/)
- The whole codes are in the
codefolder. You can use CMake to compile SPM-BP (Tested on 64 bit Ubuntu 14.04 and Windows 7 with Visual Studio 2012).
- For windows user, a compiled execuable with demo usage is provided in
- We will be happy if you cite us when using this code!
- If you want to test Stereo Matching using SPM-BP, we can share the execuable upon request.
- OpenCV 3.0
- SLIC superpixel  (included)
- [Cross-based Local Multipoint Filtering (CLMF) ] (https://sites.google.com/site/filteringtutorial/) (included)
- Fast Global Image Smoothing (FGS)  (modified and included)
 R. Achanta , A. Shaji, K. Smith, A. Lucchi,P. Fua, and S. Susstrunk, " SLIC superpixels compared to state-of-the-art superpixel methods," IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 34(11), 2274-2282, 2012.
 J. Lu, K. Shi, D. Min, L. Lin, and M. N. Do, "Cross-based local multipoint filtering," in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), Providence, Rhode Island, 2012.
 D. Min, S. Choi, J. Lu, B. Ham, K. Sohn, and M. N. Do, “Fast Global Image Smoothing Based on Weighted Least Squares,” IEEE Trans. on Image Processing (TIP), 23(12), 5638-5653, 2014.
Copyright (c) 2015, Yu Li All rights reserved.
For research and education purpose only.