Motion Coherence and Wide-baseline Matching
This work proposes modeling motion in a bilateral domain that augments spatial information with the motion itself. We use the bilateral domain to reformulate a piecewise smooth constraint as a continuous global modeling constraint. The resultant model can be robustly computed from highly noisy scattered feature points using a global minimization. We demonstrate how the model can reliably obtain large numbers of good quality correspondences over wide baselines, while keeping outliers to a minimum.
- W.-Y. Lin, F. Wang, M. Cheng, S.-K.Yeung, P. Torr, M. N. Do, and J. Lu, “CODE: Coherence Based Decision Boundaries for Feature Correspondence,” IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI), 2017. [preprint]
- W.-Y. Lin, M. Cheng, J. Lu, H. Yang, M. N. Do, and P. H. S. Torr, “Bilateral Functions for Global Motion Modeling,” in Proc. Eur. Conf. Computer Vision (ECCV), Zurich, Switzerland, Sep. 2014. [pdf]
- W.-Y. Lin, M. Cheng, K. Zheng, J. Lu, and C. Nigel, “Robust Non-parametric Data Fitting for Correspondence Modeling,” in Proc. IEEE Int. Conf. Computer Vision (ICCV), Sydney, Australia, Dec. 2013. [pdf]
- Our related work: W.-Y. Lin, S. Liu, N. Jiang, M. N. Do, P. Tan, and J. Lu, “RepMatch: Robust Feature Matching and Pose for Reconstructing Modern Cities,” European Conf. Computer Vision (ECCV), Amsterdam, Oct. 2016. [pdf][supplementary]
For more information, please visit our website for a half-day tutorial in ICME 2015.