This paper suggests 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 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.
Bilateral Functions for Global Motion Modeling, Wen-Yan Lin, Ming-Ming Cheng, Jiangbo Lu, Hongsheng Yang, Minh Do, Philip Torr, ECCV, 2014. [pdf] [bib] [project page]
Robust Non-parametric Data Fitting for Correspondence Modeling, Wen-Yan Lin, Ming-Ming Cheng, Shuai Zheng, Jiangbo Lu, Nigel Crook, IEEE International Conference on Computer Vision (IEEE ICCV), 2013. [Project page] [pdf] [bib] [Official version]